SU\G(𝔸)/K·U
Sign Up for free Log In

Author Description

Login to generate an author description

Ask a Question About This Mathematician

DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor With Application to In-Hand Manipulation

2020-02-28
Mike Lambeta , Po-Wei Chou , Stephen Tian +7 more
Despite decades of research, general purpose in-hand manipulation remains one of the unsolved challenges of robotics. One of the contributing factors that limit current robotic manipulation systems is the difficulty … Despite decades of research, general purpose in-hand manipulation remains one of the unsolved challenges of robotics. One of the contributing factors that limit current robotic manipulation systems is the difficulty of precisely sensing contact forces -- sensing and reasoning about contact forces are crucial to accurately control interactions with the environment. As a step towards enabling better robotic manipulation, we introduce DIGIT, an inexpensive, compact, and high-resolution tactile sensor geared towards in-hand manipulation. DIGIT improves upon past vision-based tactile sensors by miniaturizing the form factor to be mountable on multi-fingered hands, and by providing several design improvements that result in an easier, more repeatable manufacturing process, and enhanced reliability. We demonstrate the capabilities of the DIGIT sensor by training deep neural network model-based controllers to manipulate glass marbles in-hand with a multi-finger robotic hand. To provide the robotic community access to reliable and low-cost tactile sensors, we open-source the DIGIT design at https://digit.ml/.
View PDF Chat

Learning Image Representations Tied to Ego-Motion

2015-12-01
Dinesh Jayaraman , Kristen Grauman
Understanding how images of objects and scenes behave in response to specific ego-motions is a crucial aspect of proper visual development, yet existing visual learning methods are conspicuously disconnected from … Understanding how images of objects and scenes behave in response to specific ego-motions is a crucial aspect of proper visual development, yet existing visual learning methods are conspicuously disconnected from the physical source of their images. We propose to exploit proprioceptive motor signals to provide unsupervised regularization in convolutional neural networks to learn visual representations from egocentric video. Specifically, we enforce that our learned features exhibit equivariance, i.e, they respond predictably to transformations associated with distinct ego-motions. With three datasets, we show that our unsupervised feature learning approach significantly outperforms previous approaches on visual recognition and next-best-view prediction tasks. In the most challenging test, we show that features learned from video captured on an autonomous driving platform improve large-scale scene recognition in static images from a disjoint domain.
View PDF Chat

Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video

2016-06-01
Dinesh Jayaraman , Kristen Grauman
How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures … How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact that high-level visual signals change slowly over time, it fails to capture how the visual content changes. We propose to generalize slow feature analysis to "steady" feature analysis. The key idea is to impose a prior that higher order derivatives in the learned feature space must be small. To this end, we train a convolutional neural network with a regularizer on tuples of sequential frames from unlabeled video. It encourages feature changes over time to be smooth, i.e., similar to the most recent changes. Using five diverse datasets, including unlabeled YouTube and KITTI videos, we demonstrate our method's impact on object, scene, and action recognition tasks. We further show that our features learned from unlabeled video can even surpass a standard heavily supervised pretraining approach.
View PDF Chat

More Than a Feeling: Learning to Grasp and Regrasp Using Vision and Touch

2018-07-04
Roberto Calandra , Andrew Owens , Dinesh Jayaraman +5 more
For humans, the process of grasping an object relies heavily on rich tactile feedback. Most recent robotic grasping work, however, has been based only on visual input, and thus cannot … For humans, the process of grasping an object relies heavily on rich tactile feedback. Most recent robotic grasping work, however, has been based only on visual input, and thus cannot easily benefit from feedback after initiating contact. In this letter, we investigate how a robot can learn to use tactile information to iteratively and efficiently adjust its grasp. To this end, we propose an end-to-end action-conditional model that learns regrasping policies from raw visuo-tactile data. This model - a deep, multimodal convolutional network - predicts the outcome of a candidate grasp adjustment, and then executes a grasp by iteratively selecting the most promising actions. Our approach requires neither calibration of the tactile sensors nor any analytical modeling of contact forces, thus reducing the engineering effort required to obtain efficient grasping policies. We train our model with data from about 6450 grasping trials on a two-finger gripper equipped with GelSight high-resolution tactile sensors on each finger. Across extensive experiments, our approach outperforms a variety of baselines at 1) estimating grasp adjustment outcomes, 2) selecting efficient grasp adjustments for quick grasping, and 3) reducing the amount of force applied at the fingers, while maintaining competitive performance. Finally, we study the choices made by our model and show that it has successfully acquired useful and interpretable grasping behaviors.
View PDF Chat

Probabilistic Modeling for Human Mesh Recovery

2021-10-01
Nikos Kolotouros , Georgios Pavlakos , Dinesh Jayaraman +1 more
This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and … This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and typically regress a single estimate for a given input. In contrast to that, in this work, we propose to embrace the reconstruction ambiguity and we recast the problem as learning a mapping from the input to a distribution of plausible 3D poses. Our approach is based on the normalizing flows model and offers a series of advantages. For conventional applications, where a single 3D estimate is required, our formulation allows for efficient mode computation. Using the mode leads to performance that is comparable with the state of the art among deterministic unimodal regression models. Simultaneously, since we have access to the likelihood of each sample, we demonstrate that our model is useful in a series of downstream tasks, where we leverage the probabilistic nature of the prediction as a tool for more accurate estimation. These tasks include reconstruction from multiple uncalibrated views, as well as human model fitting, where our model acts as a powerful image-based prior for mesh recovery. Our results validate the importance of probabilistic modeling, and indicate state-of-the-art performance across a variety of settings. Code and models are available at: https://www.seas.upenn.edu/~nkolot/projects/prohmr.
View PDF Chat

Zero Shot Recognition with Unreliable Attributes

2014-01-01
Dinesh Jayaraman , Kristen Grauman
In principle, zero-shot learning makes it possible to train a recognition model simply by specifying the category's attributes. For example, with classifiers for generic attributes like \emph{striped} and \emph{four-legged}, one … In principle, zero-shot learning makes it possible to train a recognition model simply by specifying the category's attributes. For example, with classifiers for generic attributes like \emph{striped} and \emph{four-legged}, one can construct a classifier for the zebra category by enumerating which properties it possesses---even without providing zebra training images. In practice, however, the standard zero-shot paradigm suffers because attribute predictions in novel images are hard to get right. We propose a novel random forest approach to train zero-shot models that explicitly accounts for the unreliability of attribute predictions. By leveraging statistics about each attribute's error tendencies, our method obtains more robust discriminative models for the unseen classes. We further devise extensions to handle the few-shot scenario and unreliable attribute descriptions. On three datasets, we demonstrate the benefit for visual category learning with zero or few training examples, a critical domain for rare categories or categories defined on the fly.

Manipulation by Feel: Touch-Based Control with Deep Predictive Models

2019-05-01
Stephen Tian , Frederik Ebert , Dinesh Jayaraman +4 more
Touch sensing is widely acknowledged to be important for dexterous robotic manipulation, but exploiting tactile sensing for continuous, non-prehensile manipulation is challenging. General purpose control techniques that are able to … Touch sensing is widely acknowledged to be important for dexterous robotic manipulation, but exploiting tactile sensing for continuous, non-prehensile manipulation is challenging. General purpose control techniques that are able to effectively leverage tactile sensing as well as accurate physics models of contacts and forces remain largely elusive, and it is unclear how to even specify a desired behavior in terms of tactile percepts. In this paper, we take a step towards addressing these issues by combining high-resolution tactile sensing with data-driven modeling using deep neural network dynamics models. We propose deep tactile MPC, a framework for learning to perform tactile servoing from raw tactile sensor inputs, without manual supervision. We show that this method enables a robot equipped with a GelSight-style tactile sensor to manipulate a ball, analog stick, and 20-sided die, learning from unsupervised autonomous interaction and then using the learned tactile predictive model to reposition each object to user-specified configurations, indicated by a goal tactile reading. Videos, visualizations and the code are available here: https://sites.google.com/view/deeptactilempc.
View PDF Chat

Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks

2018-06-01
Dinesh Jayaraman , Kristen Grauman
It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the … It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the problem of learning to look around: if an agent has the ability to voluntarily acquire new views to observe its environment, how can it learn efficient exploratory behaviors to acquire informative visual observations? We propose a reinforcement learning solution, where the agent is rewarded for actions that reduce its uncertainty about the unobserved portions of its environment. Based on this principle, we develop a recurrent neural network-based approach to perform active completion of panoramic natural scenes and 3D object shapes. Crucially, the learned policies are not tied to any recognition task nor to the particular semantic content seen during training. As a result, 1) the learned "look around" behavior is relevant even for new tasks in unseen environments, and 2) training data acquisition involves no manual labeling. Through tests in diverse settings, we demonstrate that our approach learns useful generic policies that transfer to new unseen tasks and environments.
View PDF Chat

Causal Confusion in Imitation Learning

2019-01-01
Pim de Haan , Dinesh Jayaraman , Sergey Levine
Behavioral cloning reduces policy learning to supervised learning by training a discriminative model to predict expert actions given observations. Such discriminative models are non-causal: the training procedure is unaware of … Behavioral cloning reduces policy learning to supervised learning by training a discriminative model to predict expert actions given observations. Such discriminative models are non-causal: the training procedure is unaware of the causal structure of the interaction between the expert and the environment. We point out that ignoring causality is particularly damaging because of the distributional shift in imitation learning. In particular, it leads to a counter-intuitive "causal misidentification" phenomenon: access to more information can yield worse performance. We investigate how this problem arises, and propose a solution to combat it through targeted interventions---either environment interaction or expert queries---to determine the correct causal model. We show that causal misidentification occurs in several benchmark control domains as well as realistic driving settings, and validate our solution against DAgger and other baselines and ablations.

An Exploration of Embodied Visual Exploration

2021-02-27
Santhosh Kumar Ramakrishnan , Dinesh Jayaraman , Kristen Grauman
View PDF Chat

Pano2Vid: Automatic Cinematography for Watching 360 $$^{\circ }$$ Videos

2017-01-01
Yu-Chuan Su , Dinesh Jayaraman , Kristen Grauman
View PDF Chat

Look-Ahead Before You Leap: End-to-End Active Recognition by Forecasting the Effect of Motion

2016-01-01
Dinesh Jayaraman , Kristen Grauman
View PDF Chat

Object-Centric Representation Learning from Unlabeled Videos

2017-01-01
Ruohan Gao , Dinesh Jayaraman , Kristen Grauman
View PDF Chat

Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings

2020-01-01
Jesse Zhang , Brian Cheung , Chelsea Finn +2 more
Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous, imperiling the RL agent, other agents, and the environment. To overcome this difficulty, we propose a "safety-critical … Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous, imperiling the RL agent, other agents, and the environment. To overcome this difficulty, we propose a "safety-critical adaptation" task setting: an agent first trains in non-safety-critical "source" environments such as in a simulator, before it adapts to the target environment where failures carry heavy costs. We propose a solution approach, CARL, that builds on the intuition that prior experience in diverse environments equips an agent to estimate risk, which in turn enables relative safety through risk-averse, cautious adaptation. CARL first employs model-based RL to train a probabilistic model to capture uncertainty about transition dynamics and catastrophic states across varied source environments. Then, when exploring a new safety-critical environment with unknown dynamics, the CARL agent plans to avoid actions that could lead to catastrophic states. In experiments on car driving, cartpole balancing, half-cheetah locomotion, and robotic object manipulation, CARL successfully acquires cautious exploration behaviors, yielding higher rewards with fewer failures than strong RL adaptation baselines. Website at https://sites.google.com/berkeley.edu/carl.

VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training

2022-01-01
Yecheng Jason Ma , Shagun Sodhani , Dinesh Jayaraman +3 more
Reward and representation learning are two long-standing challenges for learning an expanding set of robot manipulation skills from sensory observations. Given the inherent cost and scarcity of in-domain, task-specific robot … Reward and representation learning are two long-standing challenges for learning an expanding set of robot manipulation skills from sensory observations. Given the inherent cost and scarcity of in-domain, task-specific robot data, learning from large, diverse, offline human videos has emerged as a promising path towards acquiring a generally useful visual representation for control; however, how these human videos can be used for general-purpose reward learning remains an open question. We introduce $\textbf{V}$alue-$\textbf{I}$mplicit $\textbf{P}$re-training (VIP), a self-supervised pre-trained visual representation capable of generating dense and smooth reward functions for unseen robotic tasks. VIP casts representation learning from human videos as an offline goal-conditioned reinforcement learning problem and derives a self-supervised dual goal-conditioned value-function objective that does not depend on actions, enabling pre-training on unlabeled human videos. Theoretically, VIP can be understood as a novel implicit time contrastive objective that generates a temporally smooth embedding, enabling the value function to be implicitly defined via the embedding distance, which can then be used to construct the reward for any goal-image specified downstream task. Trained on large-scale Ego4D human videos and without any fine-tuning on in-domain, task-specific data, VIP's frozen representation can provide dense visual reward for an extensive set of simulated and $\textbf{real-robot}$ tasks, enabling diverse reward-based visual control methods and significantly outperforming all prior pre-trained representations. Notably, VIP can enable simple, $\textbf{few-shot}$ offline RL on a suite of real-world robot tasks with as few as 20 trajectories.

Learning image representations equivariant to ego-motion.

2015-05-08
Dinesh Jayaraman , Kristen Grauman
Understanding how images of objects and scenes behave in response to specific ego-motions is a crucial aspect of proper visual development, yet existing visual learning methods are conspicuously disconnected from … Understanding how images of objects and scenes behave in response to specific ego-motions is a crucial aspect of proper visual development, yet existing visual learning methods are conspicuously disconnected from the physical source of their images. We propose to exploit proprioceptive motor signals to provide unsupervised regularization in convolutional neural networks to learn visual representations from egocentric video. Specifically, we enforce that our learned features exhibit equivariance i.e. they respond systematically to transformations associated with distinct ego-motions. With three datasets, we show that our unsupervised feature learning system significantly outperforms previous approaches on visual recognition and next-best-view prediction tasks. In the most challenging test, we show that features learned from video captured on an autonomous driving platform improve large-scale scene recognition in a disjoint domain.

Time-Agnostic Prediction: Predicting Predictable Video Frames

2018-08-23
Dinesh Jayaraman , Frederik Ebert , Alexei A. Efros +1 more
Prediction is arguably one of the most basic functions of an intelligent system. In general, the problem of predicting events in the future or between two waypoints is exceedingly difficult. … Prediction is arguably one of the most basic functions of an intelligent system. In general, the problem of predicting events in the future or between two waypoints is exceedingly difficult. However, most phenomena naturally pass through relatively predictable bottlenecks---while we cannot predict the precise trajectory of a robot arm between being at rest and holding an object up, we can be certain that it must have picked the object up. To exploit this, we decouple visual prediction from a rigid notion of time. While conventional approaches predict frames at regularly spaced temporal intervals, our time-agnostic predictors (TAP) are not tied to specific times so that they may instead discover predictable bottleneck frames no matter when they occur. We evaluate our approach for future and intermediate frame prediction across three robotic manipulation tasks. Our predictions are not only of higher visual quality, but also correspond to coherent semantic subgoals in temporally extended tasks.

REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning

2019-01-01
Brian Yang , Jesse Zhang , Vitchyr H. Pong +2 more
Standardized evaluation measures have aided in the progress of machine learning approaches in disciplines such as computer vision and machine translation. In this paper, we make the case that robotic … Standardized evaluation measures have aided in the progress of machine learning approaches in disciplines such as computer vision and machine translation. In this paper, we make the case that robotic learning would also benefit from benchmarking, and present the "REPLAB" platform for benchmarking vision-based manipulation tasks. REPLAB is a reproducible and self-contained hardware stack (robot arm, camera, and workspace) that costs about 2000 USD, occupies a cuboid of size 70x40x60 cm, and permits full assembly within a few hours. Through this low-cost, compact design, REPLAB aims to drive wide participation by lowering the barrier to entry into robotics and to enable easy scaling to many robots. We envision REPLAB as a framework for reproducible research across manipulation tasks, and as a step in this direction, we define a template for a grasping benchmark consisting of a task definition, evaluation protocol, performance measures, and a dataset of 92k grasp attempts. We implement, evaluate, and analyze several previously proposed grasping approaches to establish baselines for this benchmark. Finally, we also implement and evaluate a deep reinforcement learning approach for 3D reaching tasks on our REPLAB platform. Project page with assembly instructions, code, and videos: https://goo.gl/5F9dP4.

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

2020-01-01
Karl Pertsch , Oleh Rybkin , Frederik Ebert +3 more
The ability to predict and plan into the future is fundamental for agents acting in the world. To reach a faraway goal, we predict trajectories at multiple timescales, first devising … The ability to predict and plan into the future is fundamental for agents acting in the world. To reach a faraway goal, we predict trajectories at multiple timescales, first devising a coarse plan towards the goal and then gradually filling in details. In contrast, current learning approaches for visual prediction and planning fail on long-horizon tasks as they generate predictions (1) without considering goal information, and (2) at the finest temporal resolution, one step at a time. In this work we propose a framework for visual prediction and planning that is able to overcome both of these limitations. First, we formulate the problem of predicting towards a goal and propose the corresponding class of latent space goal-conditioned predictors (GCPs). GCPs significantly improve planning efficiency by constraining the search space to only those trajectories that reach the goal. Further, we show how GCPs can be naturally formulated as hierarchical models that, given two observations, predict an observation between them, and by recursively subdividing each part of the trajectory generate complete sequences. This divide-and-conquer strategy is effective at long-term prediction, and enables us to design an effective hierarchical planning algorithm that optimizes trajectories in a coarse-to-fine manner. We show that by using both goal-conditioning and hierarchical prediction, GCPs enable us to solve visual planning tasks with much longer horizon than previously possible.

Time-Agnostic Prediction: Predicting Predictable Video Frames

2018-01-01
Dinesh Jayaraman , Frederik Ebert , Alexei A. Efros +1 more
Prediction is arguably one of the most basic functions of an intelligent system. In general, the problem of predicting events in the future or between two waypoints is exceedingly difficult. … Prediction is arguably one of the most basic functions of an intelligent system. In general, the problem of predicting events in the future or between two waypoints is exceedingly difficult. However, most phenomena naturally pass through relatively predictable bottlenecks---while we cannot predict the precise trajectory of a robot arm between being at rest and holding an object up, we can be certain that it must have picked the object up. To exploit this, we decouple visual prediction from a rigid notion of time. While conventional approaches predict frames at regularly spaced temporal intervals, our time-agnostic predictors (TAP) are not tied to specific times so that they may instead discover predictable "bottleneck" frames no matter when they occur. We evaluate our approach for future and intermediate frame prediction across three robotic manipulation tasks. Our predictions are not only of higher visual quality, but also correspond to coherent semantic subgoals in temporally extended tasks.
View PDF Chat

Model-Based Inverse Reinforcement Learning from Visual Demonstrations

2020-01-01
Neha Das , Sarah Bechtle , Todor Davchev +3 more
Scaling model-based inverse reinforcement learning (IRL) to real robotic manipulation tasks with unknown dynamics remains an open problem. The key challenges lie in learning good dynamics models, developing algorithms that … Scaling model-based inverse reinforcement learning (IRL) to real robotic manipulation tasks with unknown dynamics remains an open problem. The key challenges lie in learning good dynamics models, developing algorithms that scale to high-dimensional state-spaces and being able to learn from both visual and proprioceptive demonstrations. In this work, we present a gradient-based inverse reinforcement learning framework that utilizes a pre-trained visual dynamics model to learn cost functions when given only visual human demonstrations. The learned cost functions are then used to reproduce the demonstrated behavior via visual model predictive control. We evaluate our framework on hardware on two basic object manipulation tasks.

Emergence of exploratory look-around behaviors through active observation completion

2019-05-15
Santhosh Kumar Ramakrishnan , Dinesh Jayaraman , Kristen Grauman
Standard computer vision systems assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself. We address the … Standard computer vision systems assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself. We address the problem of learning to look around: How can an agent learn to acquire informative visual observations? We propose a reinforcement learning solution, where the agent is rewarded for reducing its uncertainty about the unobserved portions of its environment. Specifically, the agent is trained to select a short sequence of glimpses, after which it must infer the appearance of its full environment. To address the challenge of sparse rewards, we further introduce sidekick policy learning, which exploits the asymmetry in observability between training and test time. The proposed methods learned observation policies that not only performed the completion task for which they were trained but also generalized to exhibit useful "look-around" behavior for a range of active perception tasks.
View PDF Chat

Likelihood-Based Diverse Sampling for Trajectory Forecasting

2021-10-01
Yecheng Jason , Jeevana Priya Inala , Dinesh Jayaraman +1 more
Forecasting complex vehicle and pedestrian multi-modal distributions requires powerful probabilistic approaches. Normalizing flows (NF) have recently emerged as an attractive tool to model such distributions. However, a key drawback is … Forecasting complex vehicle and pedestrian multi-modal distributions requires powerful probabilistic approaches. Normalizing flows (NF) have recently emerged as an attractive tool to model such distributions. However, a key drawback is that independent samples drawn from a flow model often do not adequately capture all the modes in the underlying distribution. We propose Likelihood-Based Diverse Sampling (LDS), a method for improving the quality and the diversity of trajectory samples from a pre-trained flow model. Rather than producing individual samples, LDS produces a set of trajectories in one shot. Given a pre-trained forecasting flow model, we train LDS using gradients from the model, to optimize an objective function that rewards high likelihood for individual trajectories in the predicted set, together with high spatial separation among trajectories. LDS outperforms state-of-art post-hoc neural diverse forecasting methods for various pre-trained flow models as well as conditional variational autoencoder (CVAE) models. Crucially, it can also be used for transductive trajectory forecasting, where the diverse forecasts are trained on-the-fly on unlabeled test examples. LDS is easy to implement, and we show that it offers a simple plug-in improvement over baselines on two challenging benchmarks. Code is at: https://github.com/JasonMa2016/LDS
View PDF Chat

Eureka: Human-Level Reward Design via Coding Large Language Models

2023-01-01
Yecheng Jason Ma , William Liang , Guanzhi Wang +6 more
Large Language Models (LLMs) have excelled as high-level semantic planners for sequential decision-making tasks. However, harnessing them to learn complex low-level manipulation tasks, such as dexterous pen spinning, remains an … Large Language Models (LLMs) have excelled as high-level semantic planners for sequential decision-making tasks. However, harnessing them to learn complex low-level manipulation tasks, such as dexterous pen spinning, remains an open problem. We bridge this fundamental gap and present Eureka, a human-level reward design algorithm powered by LLMs. Eureka exploits the remarkable zero-shot generation, code-writing, and in-context improvement capabilities of state-of-the-art LLMs, such as GPT-4, to perform evolutionary optimization over reward code. The resulting rewards can then be used to acquire complex skills via reinforcement learning. Without any task-specific prompting or pre-defined reward templates, Eureka generates reward functions that outperform expert human-engineered rewards. In a diverse suite of 29 open-source RL environments that include 10 distinct robot morphologies, Eureka outperforms human experts on 83% of the tasks, leading to an average normalized improvement of 52%. The generality of Eureka also enables a new gradient-free in-context learning approach to reinforcement learning from human feedback (RLHF), readily incorporating human inputs to improve the quality and the safety of the generated rewards without model updating. Finally, using Eureka rewards in a curriculum learning setting, we demonstrate for the first time, a simulated Shadow Hand capable of performing pen spinning tricks, adeptly manipulating a pen in circles at rapid speed.

Manipulation by Feel: Touch-Based Control with Deep Predictive Models

2019-01-01
Stephen Tian , Frederik Ebert , Dinesh Jayaraman +4 more
Touch sensing is widely acknowledged to be important for dexterous robotic manipulation, but exploiting tactile sensing for continuous, non-prehensile manipulation is challenging. General purpose control techniques that are able to … Touch sensing is widely acknowledged to be important for dexterous robotic manipulation, but exploiting tactile sensing for continuous, non-prehensile manipulation is challenging. General purpose control techniques that are able to effectively leverage tactile sensing as well as accurate physics models of contacts and forces remain largely elusive, and it is unclear how to even specify a desired behavior in terms of tactile percepts. In this paper, we take a step towards addressing these issues by combining high-resolution tactile sensing with data-driven modeling using deep neural network dynamics models. We propose deep tactile MPC, a framework for learning to perform tactile servoing from raw tactile sensor inputs, without manual supervision. We show that this method enables a robot equipped with a GelSight-style tactile sensor to manipulate a ball, analog stick, and 20-sided die, learning from unsupervised autonomous interaction and then using the learned tactile predictive model to reposition each object to user-specified configurations, indicated by a goal tactile reading. Videos, visualizations and the code are available here: https://sites.google.com/view/deeptactilempc

ShapeCodes: Self-supervised Feature Learning by Lifting Views to Viewgrids

2018-01-01
Dinesh Jayaraman , Ruohan Gao , Kristen Grauman
View PDF Chat

SMiRL: Surprise Minimizing RL in Dynamic Environments

2019-12-11
Glen Berseth , Daniel Geng , Coline Devin +3 more
Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche. We propose that such a struggle to achieve and preserve order might offer a … Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche. We propose that such a struggle to achieve and preserve order might offer a principle for the emergence of useful behaviors in artificial agents. We formalize this idea into an unsupervised reinforcement learning method called surprise minimizing reinforcement learning (SMiRL). SMiRL alternates between learning a density model to evaluate the surprise of a stimulus, and improving the policy to seek more predictable stimuli. The policy seeks out stable and repeatable situations that counteract the environment's prevailing sources of entropy. This might include avoiding other hostile agents, or finding a stable, balanced pose for a bipedal robot in the face of disturbance forces. We demonstrate that our surprise minimizing agents can successfully play Tetris, Doom, control a humanoid to avoid falls, and navigate to escape enemies in a maze without any task-specific reward supervision. We further show that SMiRL can be used together with standard task rewards to accelerate reward-driven learning.

LIV: Language-Image Representations and Rewards for Robotic Control

2023-01-01
Yecheng Jason Ma , William Liang , Vaidehi Som +4 more
We present Language-Image Value learning (LIV), a unified objective for vision-language representation and reward learning from action-free videos with text annotations. Exploiting a novel connection between dual reinforcement learning and … We present Language-Image Value learning (LIV), a unified objective for vision-language representation and reward learning from action-free videos with text annotations. Exploiting a novel connection between dual reinforcement learning and mutual information contrastive learning, the LIV objective trains a multi-modal representation that implicitly encodes a universal value function for tasks specified as language or image goals. We use LIV to pre-train the first control-centric vision-language representation from large human video datasets such as EpicKitchen. Given only a language or image goal, the pre-trained LIV model can assign dense rewards to each frame in videos of unseen robots or humans attempting that task in unseen environments. Further, when some target domain-specific data is available, the same objective can be used to fine-tune and improve LIV and even other pre-trained representations for robotic control and reward specification in that domain. In our experiments on several simulated and real-world robot environments, LIV models consistently outperform the best prior input state representations for imitation learning, as well as reward specification methods for policy synthesis. Our results validate the advantages of joint vision-language representation and reward learning within the unified, compact LIV framework.
View PDF Chat

Fighting Copycat Agents in Behavioral Cloning from Observation Histories

2020-01-01
Chuan Wen , Jierui Lin , Trevor Darrell +2 more
Imitation learning trains policies to map from input observations to the actions that an expert would choose. In this setting, distribution shift frequently exacerbates the effect of misattributing expert actions … Imitation learning trains policies to map from input observations to the actions that an expert would choose. In this setting, distribution shift frequently exacerbates the effect of misattributing expert actions to nuisance correlates among the observed variables. We observe that a common instance of this causal confusion occurs in partially observed settings when expert actions are strongly correlated over time: the imitator learns to cheat by predicting the expert's previous action, rather than the next action. To combat this "copycat problem", we propose an adversarial approach to learn a feature representation that removes excess information about the previous expert action nuisance correlate, while retaining the information necessary to predict the next action. In our experiments, our approach improves performance significantly across a variety of partially observed imitation learning tasks.
View PDF Chat

Conservative Offline Distributional Reinforcement Learning

2021-01-01
Yecheng Jason Ma , Dinesh Jayaraman , Osbert Bastani
Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requires quantifying the … Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requires quantifying the risk associated with different actions. In the online setting, distributional RL algorithms do so by learning the distribution over returns (i.e., cumulative rewards) instead of the expected return; beyond quantifying risk, they have also been shown to learn better representations for planning. We propose Conservative Offline Distributional Actor Critic (CODAC), an offline RL algorithm suitable for both risk-neutral and risk-averse domains. CODAC adapts distributional RL to the offline setting by penalizing the predicted quantiles of the return for out-of-distribution actions. We prove that CODAC learns a conservative return distribution -- in particular, for finite MDPs, CODAC converges to an uniform lower bound on the quantiles of the return distribution; our proof relies on a novel analysis of the distributional Bellman operator. In our experiments, on two challenging robot navigation tasks, CODAC successfully learns risk-averse policies using offline data collected purely from risk-neutral agents. Furthermore, CODAC is state-of-the-art on the D4RL MuJoCo benchmark in terms of both expected and risk-sensitive performance.
View PDF Chat

Model-Based Inverse Reinforcement Learning from Visual Demonstrations

2020-01-01
Neha Das , Sarah Bechtle , Todor Davchev +3 more
Scaling model-based inverse reinforcement learning (IRL) to real robotic manipulation tasks with unknown dynamics remains an open problem. The key challenges lie in learning good dynamics models, developing algorithms that … Scaling model-based inverse reinforcement learning (IRL) to real robotic manipulation tasks with unknown dynamics remains an open problem. The key challenges lie in learning good dynamics models, developing algorithms that scale to high-dimensional state-spaces and being able to learn from both visual and proprioceptive demonstrations. In this work, we present a gradient-based inverse reinforcement learning framework that utilizes a pre-trained visual dynamics model to learn cost functions when given only visual human demonstrations. The learned cost functions are then used to reproduce the demonstrated behavior via visual model predictive control. We evaluate our framework on hardware on two basic object manipulation tasks.

Diverse Sampling for Normalizing Flow Based Trajectory Forecasting.

2020-11-30
Yecheng Jason , Jeevana Priya Inala , Dinesh Jayaraman +1 more
For autonomous cars to drive safely and effectively, they must anticipate the stochastic future trajectories of other agents in the scene, such as pedestrians and other cars. Forecasting such complex … For autonomous cars to drive safely and effectively, they must anticipate the stochastic future trajectories of other agents in the scene, such as pedestrians and other cars. Forecasting such complex multi-modal distributions requires powerful probabilistic approaches. Normalizing flows have recently emerged as an attractive tool to model such distributions. However, when generating trajectory predictions from a flow model, a key drawback is that independent samples often do not adequately capture all the modes in the underlying distribution. We propose Diversity Sampling for Flow (DSF), a method for improving the quality and the diversity of trajectory samples from a pre-trained flow model. Rather than producing individual samples, DSF produces a set of trajectories in one shot. Given a pre-trained forecasting flow model, we train DSF using gradients from the model, to optimize an objective function that rewards high likelihood for individual trajectories in the predicted set, together with high spatial separation between trajectories. DSF is easy to implement, and we show that it offers a simple plug-in improvement for several existing flow-based forecasting models, achieving state-of-art results on two challenging vehicle and pedestrian forecasting benchmarks.

Slow and steady feature analysis: higher order temporal coherence in video

2015-06-15
Dinesh Jayaraman , Kristen Grauman
How can unlabeled video augment visual learning? Existing methods perform feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the … How can unlabeled video augment visual learning? Existing methods perform feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact that high-level visual signals change slowly over time, it fails to capture *how* the visual content changes. We propose to generalize slow feature analysis to steady feature analysis. The key idea is to impose a prior that higher order derivatives in the learned feature space must be small. To this end, we train a convolutional neural network with a regularizer on tuples of sequential frames from unlabeled video. It encourages feature changes over time to be smooth, i.e., similar to the most recent changes. Using five diverse datasets, including unlabeled YouTube and KITTI videos, we demonstrate our method's impact on object, scene, and action recognition tasks. We further show that our features learned from unlabeled video can even surpass a standard heavily supervised pretraining approach.

Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion

2016-04-30
Dinesh Jayaraman , Kristen Grauman
Visual systems mounted on autonomous moving agents face the challenge of unconstrained data, but simultaneously have the opportunity to improve their performance by moving to acquire new views of test … Visual systems mounted on autonomous moving agents face the challenge of unconstrained data, but simultaneously have the opportunity to improve their performance by moving to acquire new views of test data. In this work, we first show how a recurrent neural network-based system may be trained to perform end-to-end of motion policies suited for this recognition setting. Further, we hypothesize that active vision requires an agent to have the capacity to reason about the effects of its motions on its view of the world. To verify this hypothesis, we attempt to induce this capacity in our active pipeline, by simultaneously to forecast the effects of the agent's motions on its internal representation of the environment conditional on all past views. Results across two challenging datasets confirm both that our end-to-end system successfully learns meaningful policies for active category recognition, and that learning to look ahead further boosts performance.

Unsupervised learning through one-shot image-based shape reconstruction.

2017-09-01
Dinesh Jayaraman , Ruohan Gao , Kristen Grauman
We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation. The main idea is a self-supervised training objective that, given only a single … We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation. The main idea is a self-supervised training objective that, given only a single 2D image, requires all unseen views of the object to be predictable from learned features. We implement this idea as an encoder-decoder convolutional neural network. The network maps an input image of an unknown category and unknown viewpoint to a latent space, from which a deconvolutional decoder can best lift the image to its complete viewgrid showing the object from all viewing angles. Our class-agnostic training procedure encourages the representation to capture fundamental shape primitives and semantic regularities in a data-driven manner---without manual semantic labels. Our results on two widely-used shape datasets show 1) our approach successfully learns to perform mental rotation even for objects unseen during training, and 2) the learned latent space is a powerful representation for object recognition, outperforming several existing unsupervised feature learning methods.

Object-Centric Representation Learning from Unlabeled Videos

2016-01-01
Ruohan Gao , Dinesh Jayaraman , Kristen Grauman
Supervised (pre-)training currently yields state-of-the-art performance for representation learning for visual recognition, yet it comes at the cost of (1) intensive manual annotations and (2) an inherent restriction in the … Supervised (pre-)training currently yields state-of-the-art performance for representation learning for visual recognition, yet it comes at the cost of (1) intensive manual annotations and (2) an inherent restriction in the scope of data relevant for learning. In this work, we explore unsupervised feature learning from unlabeled video. We introduce a novel object-centric approach to temporal coherence that encourages similar representations to be learned for object-like regions segmented from nearby frames. Our framework relies on a Siamese-triplet network to train a deep convolutional neural network (CNN) representation. Compared to existing temporal coherence methods, our idea has the advantage of lightweight preprocessing of the unlabeled video (no tracking required) while still being able to extract object-level regions from which to learn invariances. Furthermore, as we show in results on several standard datasets, our method typically achieves substantial accuracy gains over competing unsupervised methods for image classification and retrieval tasks.

SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments

2019-01-01
Glen Berseth , Daniel Geng , Coline Devin +4 more
Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche. We propose that such a struggle to achieve and preserve order might offer a … Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche. We propose that such a struggle to achieve and preserve order might offer a principle for the emergence of useful behaviors in artificial agents. We formalize this idea into an unsupervised reinforcement learning method called surprise minimizing reinforcement learning (SMiRL). SMiRL alternates between learning a density model to evaluate the surprise of a stimulus, and improving the policy to seek more predictable stimuli. The policy seeks out stable and repeatable situations that counteract the environment's prevailing sources of entropy. This might include avoiding other hostile agents, or finding a stable, balanced pose for a bipedal robot in the face of disturbance forces. We demonstrate that our surprise minimizing agents can successfully play Tetris, Doom, control a humanoid to avoid falls, and navigate to escape enemies in a maze without any task-specific reward supervision. We further show that SMiRL can be used together with standard task rewards to accelerate reward-driven learning.

An Exploration of Embodied Visual Exploration

2020-01-07
Santhosh Kumar Ramakrishnan , Dinesh Jayaraman , Kristen Grauman
Embodied computer vision considers perception for robots in novel, unstructured environments. Of particular importance is the embodied visual exploration problem: how might a robot equipped with a camera scope out … Embodied computer vision considers perception for robots in novel, unstructured environments. Of particular importance is the embodied visual exploration problem: how might a robot equipped with a camera scope out a new environment? Despite the progress thus far, many basic questions pertinent to this problem remain unanswered: (i) What does it mean for an agent to explore its environment well? (ii) Which methods work well, and under which assumptions and environmental settings? (iii) Where do current approaches fall short, and where might future work seek to improve? Seeking answers to these questions, we first present a taxonomy for existing visual exploration algorithms and create a standard framework for benchmarking them. We then perform a thorough empirical study of the four state-of-the-art paradigms using the proposed framework with two photorealistic simulated 3D environments, a state-of-the-art exploration architecture, and diverse evaluation metrics. Our experimental results offer insights and suggest new performance metrics and baselines for future work in visual exploration. Code, models and data are publicly available: this https URL

Prospective Learning: Principled Extrapolation to the Future

2022-01-01
Joshua T. Vogelstein , Timothy Verstynen , Konrad P. Körding +7 more
Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the assumption that the future … Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the assumption that the future will be identical to the past in distribution or change adversarially. But these assumptions can be either too optimistic or pessimistic for many problems in the real world. Real world scenarios evolve over multiple spatiotemporal scales with partially predictable dynamics. Here we reformulate the learning problem to one that centers around this idea of dynamic futures that are partially learnable. We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning. We argue that prospective learning more accurately characterizes many real world problems that (1) currently stymie existing artificial intelligence solutions and/or (2) lack adequate explanations for how natural intelligences solve them. Thus, studying prospective learning will lead to deeper insights and solutions to currently vexing challenges in both natural and artificial intelligences.

Learning image representations tied to ego-motion

2015-05-08
Dinesh Jayaraman , Kristen Grauman
Understanding how images of objects and scenes behave in response to specific ego-motions is a crucial aspect of proper visual development, yet existing visual learning methods are conspicuously disconnected from … Understanding how images of objects and scenes behave in response to specific ego-motions is a crucial aspect of proper visual development, yet existing visual learning methods are conspicuously disconnected from the physical source of their images. We propose to exploit proprioceptive motor signals to provide unsupervised regularization in convolutional neural networks to learn visual representations from egocentric video. Specifically, we enforce that our learned features exhibit equivariance i.e. they respond predictably to transformations associated with distinct ego-motions. With three datasets, we show that our unsupervised feature learning approach significantly outperforms previous approaches on visual recognition and next-best-view prediction tasks. In the most challenging test, we show that features learned from video captured on an autonomous driving platform improve large-scale scene recognition in static images from a disjoint domain.

Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming

2022-01-01
Chuan Wen , Jianing Qian , Jierui Lin +3 more
Across applications spanning supervised classification and sequential control, deep learning has been reported to find "shortcut" solutions that fail catastrophically under minor changes in the data distribution. In this paper, … Across applications spanning supervised classification and sequential control, deep learning has been reported to find "shortcut" solutions that fail catastrophically under minor changes in the data distribution. In this paper, we show empirically that DNNs can be coaxed to avoid poor shortcuts by providing an additional "priming" feature computed from key input features, usually a coarse output estimate. Priming relies on approximate domain knowledge of these task-relevant key input features, which is often easy to obtain in practical settings. For example, one might prioritize recent frames over past frames in a video input for visual imitation learning, or salient foreground over background pixels for image classification. On NICO image classification, MuJoCo continuous control, and CARLA autonomous driving, our priming strategy works significantly better than several popular state-of-the-art approaches for feature selection and data augmentation. We connect these empirical findings to recent theoretical results on DNN optimization, and argue theoretically that priming distracts the optimizer away from poor shortcuts by creating better, simpler shortcuts.
View PDF Chat

Pano2Vid: Automatic Cinematography for Watching 360$^{\circ}$ Videos

2016-01-01
Yu-Chuan Su , Dinesh Jayaraman , Kristen Grauman
We introduce the novel task of Pano2Vid $-$ automatic cinematography in panoramic 360$^{\circ}$ videos. Given a 360$^{\circ}$ video, the goal is to direct an imaginary camera to virtually capture natural-looking … We introduce the novel task of Pano2Vid $-$ automatic cinematography in panoramic 360$^{\circ}$ videos. Given a 360$^{\circ}$ video, the goal is to direct an imaginary camera to virtually capture natural-looking normal field-of-view (NFOV) video. By selecting "where to look" within the panorama at each time step, Pano2Vid aims to free both the videographer and the end viewer from the task of determining what to watch. Towards this goal, we first compile a dataset of 360$^{\circ}$ videos downloaded from the web, together with human-edited NFOV camera trajectories to facilitate evaluation. Next, we propose AutoCam, a data-driven approach to solve the Pano2Vid task. AutoCam leverages NFOV web video to discriminatively identify space-time "glimpses" of interest at each time instant, and then uses dynamic programming to select optimal human-like camera trajectories. Through experimental evaluation on multiple newly defined Pano2Vid performance measures against several baselines, we show that our method successfully produces informative videos that could conceivably have been captured by human videographers.
View PDF Chat

Conservative Offline Distributional Reinforcement Learning

2021-07-12
Yecheng Jason , Dinesh Jayaraman , Osbert Bastani
Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requires quantifying the … Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requires quantifying the risk associated with different actions. In the online setting, distributional RL algorithms do so by learning the distribution over returns (i.e., cumulative rewards) instead of the expected return; beyond quantifying risk, they have also been shown to learn better representations for planning. We propose Conservative Offline Distributional Actor Critic (CODAC), an offline RL algorithm suitable for both risk-neutral and risk-averse domains. CODAC adapts distributional RL to the offline setting by penalizing the predicted quantiles of the return for out-of-distribution actions. We prove that CODAC learns a conservative return distribution -- in particular, for finite MDPs, CODAC converges to an uniform lower bound on the quantiles of the return distribution; our proof relies on a novel analysis of the distributional Bellman operator. In our experiments, on two challenging robot navigation tasks, CODAC successfully learns risk-averse policies using offline data collected purely from risk-neutral agents. Furthermore, CODAC is state-of-the-art on the D4RL MuJoCo benchmark in terms of both expected and risk-sensitive performance.

How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression

2022-01-01
Yecheng Jason Ma , Jason Yan , Dinesh Jayaraman +1 more
Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets. We propose $\textbf{Go}$al-conditioned $f$-$\textbf{A}$dvantage $\textbf{R}$egression (GoFAR), a novel regression-based offline … Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets. We propose $\textbf{Go}$al-conditioned $f$-$\textbf{A}$dvantage $\textbf{R}$egression (GoFAR), a novel regression-based offline GCRL algorithm derived from a state-occupancy matching perspective; the key intuition is that the goal-reaching task can be formulated as a state-occupancy matching problem between a dynamics-abiding imitator agent and an expert agent that directly teleports to the goal. In contrast to prior approaches, GoFAR does not require any hindsight relabeling and enjoys uninterleaved optimization for its value and policy networks. These distinct features confer GoFAR with much better offline performance and stability as well as statistical performance guarantee that is unattainable for prior methods. Furthermore, we demonstrate that GoFAR's training objectives can be re-purposed to learn an agent-independent goal-conditioned planner from purely offline source-domain data, which enables zero-shot transfer to new target domains. Through extensive experiments, we validate GoFAR's effectiveness in various problem settings and tasks, significantly outperforming prior state-of-art. Notably, on a real robotic dexterous manipulation task, while no other method makes meaningful progress, GoFAR acquires complex manipulation behavior that successfully accomplishes diverse goals.
View PDF Chat

Vision-based Perimeter Defense via Multiview Pose Estimation

2022-01-01
Elijah S. Lee , Giuseppe Loianno , Dinesh Jayaraman +1 more
Previous studies in the perimeter defense game have largely focused on the fully observable setting where the true player states are known to all players. However, this is unrealistic for … Previous studies in the perimeter defense game have largely focused on the fully observable setting where the true player states are known to all players. However, this is unrealistic for practical implementation since defenders may have to perceive the intruders and estimate their states. In this work, we study the perimeter defense game in a photo-realistic simulator and the real world, requiring defenders to estimate intruder states from vision. We train a deep machine learning-based system for intruder pose detection with domain randomization that aggregates multiple views to reduce state estimation errors and adapt the defensive strategy to account for this. We newly introduce performance metrics to evaluate the vision-based perimeter defense. Through extensive experiments, we show that our approach improves state estimation, and eventually, perimeter defense performance in both 1-defender-vs-1-intruder games, and 2-defenders-vs-1-intruder games.
View PDF Chat

DrEureka: Language Model Guided Sim-To-Real Transfer

2024-06-04
Yecheng Jason Ma , William Liang , Hung-Ju Wang +5 more
Transferring policies learned in simulation to the real world is a promising strategy for acquiring robot skills at scale. However, sim-to-real approaches typically rely on manual design and tuning of … Transferring policies learned in simulation to the real world is a promising strategy for acquiring robot skills at scale. However, sim-to-real approaches typically rely on manual design and tuning of the task reward function as well as the simulation physics parameters, rendering the process slow and human-labor intensive. In this paper, we investigate using Large Language Models (LLMs) to automate and accelerate sim-to-real design. Our LLM-guided sim-to-real approach, DrEureka, requires only the physics simulation for the target task and automatically constructs suitable reward functions and domain randomization distributions to support real-world transfer. We first demonstrate that our approach can discover sim-to-real configurations that are competitive with existing human-designed ones on quadruped locomotion and dexterous manipulation tasks. Then, we showcase that our approach is capable of solving novel robot tasks, such as quadruped balancing and walking atop a yoga ball, without iterative manual design.
View PDF Chat

Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks

2017-09-01
Dinesh Jayaraman , Kristen Grauman
It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the … It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the problem of learning to around: if a visual agent has the ability to voluntarily acquire new views to observe its environment, how can it learn efficient exploratory behaviors to acquire informative observations? We propose a reinforcement learning solution, where the agent is rewarded for actions that reduce its uncertainty about the unobserved portions of its environment. Based on this principle, we develop a recurrent neural network-based approach to perform active completion of panoramic natural scenes and 3D object shapes. Crucially, the learned policies are not tied to any recognition task nor to the particular semantic content seen during training. As a result, 1) the learned look around behavior is relevant even for new tasks in unseen environments, and 2) training data acquisition involves no manual labeling. Through tests in diverse settings, we demonstrate that our approach learns useful generic policies that transfer to new unseen tasks and environments. Completion episodes are shown at this https URL.

How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?

2021-01-01
Jingxi Xu , Bruce Lee , Nikolai Matni +1 more
The difficulty of optimal control problems has classically been characterized in terms of system properties such as minimum eigenvalues of controllability/observability gramians. We revisit these characterizations in the context of … The difficulty of optimal control problems has classically been characterized in terms of system properties such as minimum eigenvalues of controllability/observability gramians. We revisit these characterizations in the context of the increasing popularity of data-driven techniques like reinforcement learning (RL), and in control settings where input observations are high-dimensional images and transition dynamics are unknown. Specifically, we ask: to what extent are quantifiable control and perceptual difficulty metrics of a task predictive of the performance and sample complexity of data-driven controllers? We modulate two different types of partial observability in a cartpole "stick-balancing" problem -- (i) the height of one visible fixation point on the cartpole, which can be used to tune fundamental limits of performance achievable by any controller, and by (ii) the level of perception noise in the fixation point position inferred from depth or RGB images of the cartpole. In these settings, we empirically study two popular families of controllers: RL and system identification-based $H_\infty$ control, using visually estimated system state. Our results show that the fundamental limits of robust control have corresponding implications for the sample-efficiency and performance of learned perception-based controllers. Visit our project website https://jxu.ai/rl-vs-control-web for more information.

Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching

2022-01-01
Yecheng Jason Ma , Andrew Shen , Dinesh Jayaraman +1 more
We propose State Matching Offline DIstribution Correction Estimation (SMODICE), a novel and versatile regression-based offline imitation learning (IL) algorithm derived via state-occupancy matching. We show that the SMODICE objective admits … We propose State Matching Offline DIstribution Correction Estimation (SMODICE), a novel and versatile regression-based offline imitation learning (IL) algorithm derived via state-occupancy matching. We show that the SMODICE objective admits a simple optimization procedure through an application of Fenchel duality and an analytic solution in tabular MDPs. Without requiring access to expert actions, SMODICE can be effectively applied to three offline IL settings: (i) imitation from observations (IfO), (ii) IfO with dynamics or morphologically mismatched expert, and (iii) example-based reinforcement learning, which we show can be formulated as a state-occupancy matching problem. We extensively evaluate SMODICE on both gridworld environments as well as on high-dimensional offline benchmarks. Our results demonstrate that SMODICE is effective for all three problem settings and significantly outperforms prior state-of-art.
View PDF Chat

Know Thyself: Transferable Visual Control Policies Through Robot-Awareness

2021-01-01
Edward S. Hu , Kun Huang , Oleh Rybkin +1 more
Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data. How might we leverage data previously collected on another robot to reduce … Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data. How might we leverage data previously collected on another robot to reduce or even completely remove this need for robot-specific data? We propose a "robot-aware control" paradigm that achieves this by exploiting readily available knowledge about the robot. We then instantiate this in a robot-aware model-based RL policy by training modular dynamics models that couple a transferable, robot-aware world dynamics module with a robot-specific, potentially analytical, robot dynamics module. This also enables us to set up visual planning costs that separately consider the robot agent and the world. Our experiments on tabletop manipulation tasks with simulated and real robots demonstrate that these plug-in improvements dramatically boost the transferability of visual model-based RL policies, even permitting zero-shot transfer of visual manipulation skills onto new robots. Project website: https://www.seas.upenn.edu/~hued/rac
View PDF Chat

REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments

2024-12-05
Kaustubh Sridhar , Souradeep Dutta , Dinesh Jayaraman +1 more
Building generalist agents that can rapidly adapt to new environments is a key challenge for deploying AI in the digital and real worlds. Is scaling current agent architectures the most … Building generalist agents that can rapidly adapt to new environments is a key challenge for deploying AI in the digital and real worlds. Is scaling current agent architectures the most effective way to build generalist agents? We propose a novel approach to pre-train relatively small policies on relatively small datasets and adapt them to unseen environments via in-context learning, without any finetuning. Our key idea is that retrieval offers a powerful bias for fast adaptation. Indeed, we demonstrate that even a simple retrieval-based 1-nearest neighbor agent offers a surprisingly strong baseline for today's state-of-the-art generalist agents. From this starting point, we construct a semi-parametric agent, REGENT, that trains a transformer-based policy on sequences of queries and retrieved neighbors. REGENT can generalize to unseen robotics and game-playing environments via retrieval augmentation and in-context learning, achieving this with up to 3x fewer parameters and up to an order-of-magnitude fewer pre-training datapoints, significantly outperforming today's state-of-the-art generalist agents. Website: https://kaustubhsridhar.github.io/regent-research
View PDF Chat

Vision Language Models are In-Context Value Learners

2024-11-07
Yecheng Jason Ma , Joey Hejna , Ayzaan Wahid +7 more
Predicting temporal progress from visual trajectories is important for intelligent robots that can learn, adapt, and improve. However, learning such progress estimator, or temporal value function, across different tasks and … Predicting temporal progress from visual trajectories is important for intelligent robots that can learn, adapt, and improve. However, learning such progress estimator, or temporal value function, across different tasks and domains requires both a large amount of diverse data and methods which can scale and generalize. To address these challenges, we present Generative Value Learning (\GVL), a universal value function estimator that leverages the world knowledge embedded in vision-language models (VLMs) to predict task progress. Naively asking a VLM to predict values for a video sequence performs poorly due to the strong temporal correlation between successive frames. Instead, GVL poses value estimation as a temporal ordering problem over shuffled video frames; this seemingly more challenging task encourages VLMs to more fully exploit their underlying semantic and temporal grounding capabilities to differentiate frames based on their perceived task progress, consequently producing significantly better value predictions. Without any robot or task specific training, GVL can in-context zero-shot and few-shot predict effective values for more than 300 distinct real-world tasks across diverse robot platforms, including challenging bimanual manipulation tasks. Furthermore, we demonstrate that GVL permits flexible multi-modal in-context learning via examples from heterogeneous tasks and embodiments, such as human videos. The generality of GVL enables various downstream applications pertinent to visuomotor policy learning, including dataset filtering, success detection, and advantage-weighted regression -- all without any model training or finetuning.
View PDF Chat

Eurekaverse: Environment Curriculum Generation via Large Language Models

2024-11-03
William Liang , Sam Wang , Hung-Ju Wang +3 more
Recent work has demonstrated that a promising strategy for teaching robots a wide range of complex skills is by training them on a curriculum of progressively more challenging environments. However, … Recent work has demonstrated that a promising strategy for teaching robots a wide range of complex skills is by training them on a curriculum of progressively more challenging environments. However, developing an effective curriculum of environment distributions currently requires significant expertise, which must be repeated for every new domain. Our key insight is that environments are often naturally represented as code. Thus, we probe whether effective environment curriculum design can be achieved and automated via code generation by large language models (LLM). In this paper, we introduce Eurekaverse, an unsupervised environment design algorithm that uses LLMs to sample progressively more challenging, diverse, and learnable environments for skill training. We validate Eurekaverse's effectiveness in the domain of quadrupedal parkour learning, in which a quadruped robot must traverse through a variety of obstacle courses. The automatic curriculum designed by Eurekaverse enables gradual learning of complex parkour skills in simulation and can successfully transfer to the real-world, outperforming manual training courses designed by humans.
View PDF Chat

Task-Oriented Hierarchical Object Decomposition for Visuomotor Control

2024-11-02
Jianing Qian , Yunshuang Li , Bernadette Bucher +1 more
Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely task-agnostic, these … Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely task-agnostic, these representations cannot effectively ignore any task-irrelevant information in the scene, and (2) They often lack the representational capacity to handle unconstrained/complex real-world scenes. Instead, we propose to train a large combinatorial family of representations organized by scene entities: objects and object parts. This hierarchical object decomposition for task-oriented representations (HODOR) permits selectively assembling different representations specific to each task while scaling in representational capacity with the complexity of the scene and the task. In our experiments, we find that HODOR outperforms prior pre-trained representations, both scene vector representations and object-centric representations, for sample-efficient imitation learning across 5 simulated and 5 real-world manipulation tasks. We further find that the invariances captured in HODOR are inherited into downstream policies, which can robustly generalize to out-of-distribution test conditions, permitting zero-shot skill chaining. Appendix, code, and videos: https://sites.google.com/view/hodor-corl24.
View PDF Chat

Learning to Achieve Goals with Belief State Transformers

2024-10-30
Edward S. Hu , Kwangjun Ahn , Qinghua Liu +6 more
We introduce the "Belief State Transformer", a next-token predictor that takes both a prefix and suffix as inputs, with a novel objective of predicting both the next token for the … We introduce the "Belief State Transformer", a next-token predictor that takes both a prefix and suffix as inputs, with a novel objective of predicting both the next token for the prefix and the previous token for the suffix. The Belief State Transformer effectively learns to solve challenging problems that conventional forward-only transformers struggle with, in a domain-independent fashion. Key to this success is learning a compact belief state that captures all relevant information necessary for accurate predictions. Empirical ablations show that each component of the model is essential in difficult scenarios where standard Transformers fall short. For the task of story writing with known prefixes and suffixes, our approach outperforms the Fill-in-the-Middle method for reaching known goals and demonstrates improved performance even when the goals are unknown. Altogether, the Belief State Transformer enables more efficient goal-conditioned decoding, better test-time inference, and high-quality text representations on small scale problems.
View PDF Chat

Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model

2024-10-03
Long Bao Le , Jason Xie , William Liang +7 more
Interactive 3D simulated objects are crucial in AR/VR, animations, and robotics, driving immersive experiences and advanced automation. However, creating these articulated objects requires extensive human effort and expertise, limiting their … Interactive 3D simulated objects are crucial in AR/VR, animations, and robotics, driving immersive experiences and advanced automation. However, creating these articulated objects requires extensive human effort and expertise, limiting their broader applications. To overcome this challenge, we present Articulate-Anything, a system that automates the articulation of diverse, complex objects from many input modalities, including text, images, and videos. Articulate-Anything leverages vision-language models (VLMs) to generate code that can be compiled into an interactable digital twin for use in standard 3D simulators. Our system exploits existing 3D asset datasets via a mesh retrieval mechanism, along with an actor-critic system that iteratively proposes, evaluates, and refines solutions for articulating the objects, self-correcting errors to achieve a robust outcome. Qualitative evaluations demonstrate Articulate-Anything's capability to articulate complex and even ambiguous object affordances by leveraging rich grounded inputs. In extensive quantitative experiments on the standard PartNet-Mobility dataset, Articulate-Anything substantially outperforms prior work, increasing the success rate from 8.7-11.6% to 75% and setting a new bar for state-of-the-art performance. We further showcase the utility of our generated assets by using them to train robotic policies for fine-grained manipulation tasks that go beyond basic pick and place.
View PDF Chat

Leveraging Symmetry to Accelerate Learning of Trajectory Tracking Controllers for Free-Flying Robotic Systems

2024-09-17
Jake Welde , N.J. Rao , Pratik Kunapuli +2 more
Tracking controllers enable robotic systems to accurately follow planned reference trajectories. In particular, reinforcement learning (RL) has shown promise in the synthesis of controllers for systems with complex dynamics and … Tracking controllers enable robotic systems to accurately follow planned reference trajectories. In particular, reinforcement learning (RL) has shown promise in the synthesis of controllers for systems with complex dynamics and modest online compute budgets. However, the poor sample efficiency of RL and the challenges of reward design make training slow and sometimes unstable, especially for high-dimensional systems. In this work, we leverage the inherent Lie group symmetries of robotic systems with a floating base to mitigate these challenges when learning tracking controllers. We model a general tracking problem as a Markov decision process (MDP) that captures the evolution of both the physical and reference states. Next, we prove that symmetry in the underlying dynamics and running costs leads to an MDP homomorphism, a mapping that allows a policy trained on a lower-dimensional "quotient" MDP to be lifted to an optimal tracking controller for the original system. We compare this symmetry-informed approach to an unstructured baseline, using Proximal Policy Optimization (PPO) to learn tracking controllers for three systems: the Particle (a forced point mass), the Astrobee (a fullyactuated space robot), and the Quadrotor (an underactuated system). Results show that a symmetry-aware approach both accelerates training and reduces tracking error after the same number of training steps.
View PDF Chat

DrEureka: Language Model Guided Sim-To-Real Transfer

2024-06-04
Yecheng Jason Ma , William Liang , Hung-Ju Wang +5 more
Transferring policies learned in simulation to the real world is a promising strategy for acquiring robot skills at scale. However, sim-to-real approaches typically rely on manual design and tuning of … Transferring policies learned in simulation to the real world is a promising strategy for acquiring robot skills at scale. However, sim-to-real approaches typically rely on manual design and tuning of the task reward function as well as the simulation physics parameters, rendering the process slow and human-labor intensive. In this paper, we investigate using Large Language Models (LLMs) to automate and accelerate sim-to-real design. Our LLM-guided sim-to-real approach, DrEureka, requires only the physics simulation for the target task and automatically constructs suitable reward functions and domain randomization distributions to support real-world transfer. We first demonstrate that our approach can discover sim-to-real configurations that are competitive with existing human-designed ones on quadruped locomotion and dexterous manipulation tasks. Then, we showcase that our approach is capable of solving novel robot tasks, such as quadruped balancing and walking atop a yoga ball, without iterative manual design.
View PDF Chat

Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policies

2024-05-24
Jianing Qian , Anastasios Panagopoulos , Dinesh Jayaraman
Generic re-usable pre-trained image representation encoders have become a standard component of methods for many computer vision tasks. As visual representations for robots however, their utility has been limited, leading … Generic re-usable pre-trained image representation encoders have become a standard component of methods for many computer vision tasks. As visual representations for robots however, their utility has been limited, leading to a recent wave of efforts to pre-train robotics-specific image encoders that are better suited to robotic tasks than their generic counterparts. We propose Scene Objects From Transformers, abbreviated as SOFT, a wrapper around pre-trained vision transformer (PVT) models that bridges this gap without any further training. Rather than construct representations out of only the final layer activations, SOFT individuates and locates object-like entities from PVT attentions, and describes them with PVT activations, producing an object-centric embedding. Across standard choices of generic pre-trained vision transformers PVT, we demonstrate in each case that policies trained on SOFT(PVT) far outstrip standard PVT representations for manipulation tasks in simulated and real settings, approaching the state-of-the-art robotics-aware representations. Code, appendix and videos: https://sites.google.com/view/robot-soft/
View PDF Chat

Privileged Sensing Scaffolds Reinforcement Learning

2024-05-23
Edward S. Hu , J. Frederick Springer , Oleh Rybkin +1 more
We need to look at our shoelaces as we first learn to tie them but having mastered this skill, can do it from touch alone. We call this phenomenon "sensory … We need to look at our shoelaces as we first learn to tie them but having mastered this skill, can do it from touch alone. We call this phenomenon "sensory scaffolding": observation streams that are not needed by a master might yet aid a novice learner. We consider such sensory scaffolding setups for training artificial agents. For example, a robot arm may need to be deployed with just a low-cost, robust, general-purpose camera; yet its performance may improve by having privileged training-time-only access to informative albeit expensive and unwieldy motion capture rigs or fragile tactile sensors. For these settings, we propose "Scaffolder", a reinforcement learning approach which effectively exploits privileged sensing in critics, world models, reward estimators, and other such auxiliary components that are only used at training time, to improve the target policy. For evaluating sensory scaffolding agents, we design a new "S3" suite of ten diverse simulated robotic tasks that explore a wide range of practical sensor setups. Agents must use privileged camera sensing to train blind hurdlers, privileged active visual perception to help robot arms overcome visual occlusions, privileged touch sensors to train robot hands, and more. Scaffolder easily outperforms relevant prior baselines and frequently performs comparably even to policies that have test-time access to the privileged sensors. Website: https://penn-pal-lab.github.io/scaffolder/
View PDF Chat

Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policies

2024-05-13
Jianing Qian , Anastasios Panagopoulos , Dinesh Jayaraman
View PDF Chat

Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Models

2024-05-13
Junyao Shi , Jianing Qian , Yecheng Jason +1 more
View PDF Chat

Universal Visual Decomposer: Long-Horizon Manipulation Made Easy

2024-05-13
Zichen Zhang , Yunshuang Li , Osbert Bastani +4 more
View PDF Chat

Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport

2024-05-13
Sriram Narayanan , Dinesh Jayaraman , Manmohan Chandraker
View PDF Chat

Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Models

2024-04-20
Junyao Shi , Jianing Qian , Yecheng Jason Ma +1 more
There have recently been large advances both in pre-training visual representations for robotic control and segmenting unknown category objects in general images. To leverage these for improved robot learning, we … There have recently been large advances both in pre-training visual representations for robotic control and segmenting unknown category objects in general images. To leverage these for improved robot learning, we propose $\textbf{POCR}$, a new framework for building pre-trained object-centric representations for robotic control. Building on theories of "what-where" representations in psychology and computer vision, we use segmentations from a pre-trained model to stably locate across timesteps, various entities in the scene, capturing "where" information. To each such segmented entity, we apply other pre-trained models that build vector descriptions suitable for robotic control tasks, thus capturing "what" the entity is. Thus, our pre-trained object-centric representations for control are constructed by appropriately combining the outputs of off-the-shelf pre-trained models, with no new training. On various simulated and real robotic tasks, we show that imitation policies for robotic manipulators trained on POCR achieve better performance and systematic generalization than state of the art pre-trained representations for robotics, as well as prior object-centric representations that are typically trained from scratch.
View PDF Chat

DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

2024-03-19
Alexander Khazatsky , Karl Pertsch , Suraj Nair +7 more
The creation of large, diverse, high-quality robot manipulation datasets is an important stepping stone on the path toward more capable and robust robotic manipulation policies. However, creating such datasets is … The creation of large, diverse, high-quality robot manipulation datasets is an important stepping stone on the path toward more capable and robust robotic manipulation policies. However, creating such datasets is challenging: collecting robot manipulation data in diverse environments poses logistical and safety challenges and requires substantial investments in hardware and human labour. As a result, even the most general robot manipulation policies today are mostly trained on data collected in a small number of environments with limited scene and task diversity. In this work, we introduce DROID (Distributed Robot Interaction Dataset), a diverse robot manipulation dataset with 76k demonstration trajectories or 350 hours of interaction data, collected across 564 scenes and 84 tasks by 50 data collectors in North America, Asia, and Europe over the course of 12 months. We demonstrate that training with DROID leads to policies with higher performance and improved generalization ability. We open source the full dataset, policy learning code, and a detailed guide for reproducing our robot hardware setup.
View PDF Chat

Can Transformers Capture Spatial Relations between Objects?

2024-03-01
Chuan Wen , Dinesh Jayaraman , Yang Gao
Spatial relationships between objects represent key scene information for humans to understand and interact with the world. To study the capability of current computer vision systems to recognize physically grounded … Spatial relationships between objects represent key scene information for humans to understand and interact with the world. To study the capability of current computer vision systems to recognize physically grounded spatial relations, we start by proposing precise relation definitions that permit consistently annotating a benchmark dataset. Despite the apparent simplicity of this task relative to others in the recognition literature, we observe that existing approaches perform poorly on this benchmark. We propose new approaches exploiting the long-range attention capabilities of transformers for this task, and evaluating key design principles. We identify a simple "RelatiViT" architecture and demonstrate that it outperforms all current approaches. To our knowledge, this is the first method to convincingly outperform naive baselines on spatial relation prediction in in-the-wild settings. The code and datasets are available in \url{https://sites.google.com/view/spatial-relation}.
View PDF Chat

Dynamic Grasping with a Learned Meta-Controller

2023-01-01
Yinsen Jia , Jingxi Xu , Dinesh Jayaraman +1 more
Grasping moving objects is a challenging task that requires multiple submodules such as object pose predictor, arm motion planner, etc. Each submodule operates under its own set of meta-parameters. For … Grasping moving objects is a challenging task that requires multiple submodules such as object pose predictor, arm motion planner, etc. Each submodule operates under its own set of meta-parameters. For example, how far the pose predictor should look into the future (i.e., look-ahead time) and the maximum amount of time the motion planner can spend planning a motion (i.e., time budget). Many previous works assign fixed values to these parameters; however, at different moments within a single episode of dynamic grasping, the optimal values should vary depending on the current scene. In this work, we propose a dynamic grasping pipeline with a meta-controller that controls the look-ahead time and time budget dynamically. We learn the meta-controller through reinforcement learning with a sparse reward. Our experiments show the meta-controller improves the grasping success rate (up to 28% in the most cluttered environment) and reduces grasping time, compared to the strongest baseline. Our meta-controller learns to reason about the reachable workspace and maintain the predicted pose within the reachable region. In addition, it assigns a small but sufficient time budget for the motion planner. Our method can handle different objects, trajectories, and obstacles. Despite being trained only with 3-6 random cuboidal obstacles, our meta-controller generalizes well to 7-9 obstacles and more realistic out-of-domain household setups with unseen obstacle shapes.

Planning Goals for Exploration

2023-01-01
Edward S. Hu , Richard Chang , Oleh Rybkin +1 more
Dropped into an unknown environment, what should an agent do to quickly learn about the environment and how to accomplish diverse tasks within it? We address this question within the … Dropped into an unknown environment, what should an agent do to quickly learn about the environment and how to accomplish diverse tasks within it? We address this question within the goal-conditioned reinforcement learning paradigm, by identifying how the agent should set its goals at training time to maximize exploration. We propose "Planning Exploratory Goals" (PEG), a method that sets goals for each training episode to directly optimize an intrinsic exploration reward. PEG first chooses goal commands such that the agent's goal-conditioned policy, at its current level of training, will end up in states with high exploration potential. It then launches an exploration policy starting at those promising states. To enable this direct optimization, PEG learns world models and adapts sampling-based planning algorithms to "plan goal commands". In challenging simulated robotics environments including a multi-legged ant robot in a maze, and a robot arm on a cluttered tabletop, PEG exploration enables more efficient and effective training of goal-conditioned policies relative to baselines and ablations. Our ant successfully navigates a long maze, and the robot arm successfully builds a stack of three blocks upon command. Website: https://penn-pal-lab.github.io/peg/
View PDF Chat

ZeroFlow: Scalable Scene Flow via Distillation

2023-01-01
Kyle Vedder , Neehar Peri , Nathaniel Chodosh +6 more
Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimization techniques, but require on the … Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimization techniques, but require on the order of tens of seconds to process full-size point clouds, making them unusable as computer vision primitives for real-time applications such as open world object detection. Feedforward methods are considerably faster, running on the order of tens to hundreds of milliseconds for full-size point clouds, but require expensive human supervision. To address both limitations, we propose Scene Flow via Distillation, a simple, scalable distillation framework that uses a label-free optimization method to produce pseudo-labels to supervise a feedforward model. Our instantiation of this framework, ZeroFlow, achieves state-of-the-art performance on the Argoverse 2 Self-Supervised Scene Flow Challenge while using zero human labels by simply training on large-scale, diverse unlabeled data. At test-time, ZeroFlow is over 1000x faster than label-free state-of-the-art optimization-based methods on full-size point clouds (34 FPS vs 0.028 FPS) and over 1000x cheaper to train on unlabeled data compared to the cost of human annotation (\$394 vs ~\$750,000). To facilitate further research, we release our code, trained model weights, and high quality pseudo-labels for the Argoverse 2 and Waymo Open datasets at https://vedder.io/zeroflow.html

TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching

2023-01-01
Yecheng Jason Ma , Kausik Sivakumar , Jason Yan +2 more
Standard model-based reinforcement learning (MBRL) approaches fit a transition model of the environment to all past experience, but this wastes model capacity on data that is irrelevant for policy improvement. … Standard model-based reinforcement learning (MBRL) approaches fit a transition model of the environment to all past experience, but this wastes model capacity on data that is irrelevant for policy improvement. We instead propose a new "transition occupancy matching" (TOM) objective for MBRL model learning: a model is good to the extent that the current policy experiences the same distribution of transitions inside the model as in the real environment. We derive TOM directly from a novel lower bound on the standard reinforcement learning objective. To optimize TOM, we show how to reduce it to a form of importance weighted maximum-likelihood estimation, where the automatically computed importance weights identify policy-relevant past experiences from a replay buffer, enabling stable optimization. TOM thus offers a plug-and-play model learning sub-routine that is compatible with any backbone MBRL algorithm. On various Mujoco continuous robotic control tasks, we show that TOM successfully focuses model learning on policy-relevant experience and drives policies faster to higher task rewards than alternative model learning approaches.
View PDF Chat

LIV: Language-Image Representations and Rewards for Robotic Control

2023-01-01
Yecheng Jason Ma , William Liang , Vaidehi Som +4 more
We present Language-Image Value learning (LIV), a unified objective for vision-language representation and reward learning from action-free videos with text annotations. Exploiting a novel connection between dual reinforcement learning and … We present Language-Image Value learning (LIV), a unified objective for vision-language representation and reward learning from action-free videos with text annotations. Exploiting a novel connection between dual reinforcement learning and mutual information contrastive learning, the LIV objective trains a multi-modal representation that implicitly encodes a universal value function for tasks specified as language or image goals. We use LIV to pre-train the first control-centric vision-language representation from large human video datasets such as EpicKitchen. Given only a language or image goal, the pre-trained LIV model can assign dense rewards to each frame in videos of unseen robots or humans attempting that task in unseen environments. Further, when some target domain-specific data is available, the same objective can be used to fine-tune and improve LIV and even other pre-trained representations for robotic control and reward specification in that domain. In our experiments on several simulated and real-world robot environments, LIV models consistently outperform the best prior input state representations for imitation learning, as well as reward specification methods for policy synthesis. Our results validate the advantages of joint vision-language representation and reward learning within the unified, compact LIV framework.
View PDF Chat

Memory-Consistent Neural Networks for Imitation Learning

2023-01-01
Kaustubh Sridhar , Souradeep Dutta , Dinesh Jayaraman +2 more
Imitation learning considerably simplifies policy synthesis compared to alternative approaches by exploiting access to expert demonstrations. For such imitation policies, errors away from the training samples are particularly critical. Even … Imitation learning considerably simplifies policy synthesis compared to alternative approaches by exploiting access to expert demonstrations. For such imitation policies, errors away from the training samples are particularly critical. Even rare slip-ups in the policy action outputs can compound quickly over time, since they lead to unfamiliar future states where the policy is still more likely to err, eventually causing task failures. We revisit simple supervised ``behavior cloning'' for conveniently training the policy from nothing more than pre-recorded demonstrations, but carefully design the model class to counter the compounding error phenomenon. Our ``memory-consistent neural network'' (MCNN) outputs are hard-constrained to stay within clearly specified permissible regions anchored to prototypical ``memory'' training samples. We provide a guaranteed upper bound for the sub-optimality gap induced by MCNN policies. Using MCNNs on 10 imitation learning tasks, with MLP, Transformer, and Diffusion backbones, spanning dexterous robotic manipulation and driving, proprioceptive inputs and visual inputs, and varying sizes and types of demonstration data, we find large and consistent gains in performance, validating that MCNNs are better-suited than vanilla deep neural networks for imitation learning applications. Website: https://sites.google.com/view/mcnn-imitation
View PDF Chat

Universal Visual Decomposer: Long-Horizon Manipulation Made Easy

2023-01-01
Zichen Zhang , Yunshuang Li , Osbert Bastani +4 more
Real-world robotic tasks stretch over extended horizons and encompass multiple stages. Learning long-horizon manipulation tasks, however, is a long-standing challenge, and demands decomposing the overarching task into several manageable subtasks … Real-world robotic tasks stretch over extended horizons and encompass multiple stages. Learning long-horizon manipulation tasks, however, is a long-standing challenge, and demands decomposing the overarching task into several manageable subtasks to facilitate policy learning and generalization to unseen tasks. Prior task decomposition methods require task-specific knowledge, are computationally intensive, and cannot readily be applied to new tasks. To address these shortcomings, we propose Universal Visual Decomposer (UVD), an off-the-shelf task decomposition method for visual long horizon manipulation using pre-trained visual representations designed for robotic control. At a high level, UVD discovers subgoals by detecting phase shifts in the embedding space of the pre-trained representation. Operating purely on visual demonstrations without auxiliary information, UVD can effectively extract visual subgoals embedded in the videos, while incurring zero additional training cost on top of standard visuomotor policy training. Goal-conditioned policies learned with UVD-discovered subgoals exhibit significantly improved compositional generalization at test time to unseen tasks. Furthermore, UVD-discovered subgoals can be used to construct goal-based reward shaping that jump-starts temporally extended exploration for reinforcement learning. We extensively evaluate UVD on both simulation and real-world tasks, and in all cases, UVD substantially outperforms baselines across imitation and reinforcement learning settings on in-domain and out-of-domain task sequences alike, validating the clear advantage of automated visual task decomposition within the simple, compact UVD framework.

Physical learning of power-efficient solutions

2023-01-01
Menachem Stern , Sam Dillavou , Dinesh Jayaraman +2 more
As the size and ubiquity of artificial intelligence and computational machine learning (ML) models grow, their energy consumption for training and use is rapidly becoming economically and environmentally unsustainable. Neuromorphic … As the size and ubiquity of artificial intelligence and computational machine learning (ML) models grow, their energy consumption for training and use is rapidly becoming economically and environmentally unsustainable. Neuromorphic computing, or the implementation of ML in hardware, has the potential to reduce this cost. In particular, recent laboratory prototypes of self-learning electronic circuits, examples of ``physical learning machines," open the door to analog hardware that directly employs physics to learn desired functions from examples. In this work, we show that this hardware platform allows for even further reduction of energy consumption by using good initial conditions as well as a new learning algorithm. Using analytical calculations, simulation and experiment, we show that a trade-off emerges when learning dynamics attempt to minimize both the error and the power consumption of the solution--greater power reductions can be achieved at the cost of decreasing solution accuracy. Finally, we demonstrate a practical procedure to weigh the relative importance of error and power minimization, improving power efficiency given a specific tolerance to error.

Eureka: Human-Level Reward Design via Coding Large Language Models

2023-01-01
Yecheng Jason Ma , William Liang , Guanzhi Wang +6 more
Large Language Models (LLMs) have excelled as high-level semantic planners for sequential decision-making tasks. However, harnessing them to learn complex low-level manipulation tasks, such as dexterous pen spinning, remains an … Large Language Models (LLMs) have excelled as high-level semantic planners for sequential decision-making tasks. However, harnessing them to learn complex low-level manipulation tasks, such as dexterous pen spinning, remains an open problem. We bridge this fundamental gap and present Eureka, a human-level reward design algorithm powered by LLMs. Eureka exploits the remarkable zero-shot generation, code-writing, and in-context improvement capabilities of state-of-the-art LLMs, such as GPT-4, to perform evolutionary optimization over reward code. The resulting rewards can then be used to acquire complex skills via reinforcement learning. Without any task-specific prompting or pre-defined reward templates, Eureka generates reward functions that outperform expert human-engineered rewards. In a diverse suite of 29 open-source RL environments that include 10 distinct robot morphologies, Eureka outperforms human experts on 83% of the tasks, leading to an average normalized improvement of 52%. The generality of Eureka also enables a new gradient-free in-context learning approach to reinforcement learning from human feedback (RLHF), readily incorporating human inputs to improve the quality and the safety of the generated rewards without model updating. Finally, using Eureka rewards in a curriculum learning setting, we demonstrate for the first time, a simulated Shadow Hand capable of performing pen spinning tricks, adeptly manipulating a pen in circles at rapid speed.

TLControl: Trajectory and Language Control for Human Motion Synthesis

2023-01-01
Weilin Wan , Zhiyang Dou , Taku Komura +3 more
Controllable human motion synthesis is essential for applications in AR/VR, gaming, movies, and embodied AI. Existing methods often focus solely on either language or full trajectory control, lacking precision in … Controllable human motion synthesis is essential for applications in AR/VR, gaming, movies, and embodied AI. Existing methods often focus solely on either language or full trajectory control, lacking precision in synthesizing motions aligned with user-specified trajectories, especially for multi-joint control. To address these issues, we present TLControl, a new method for realistic human motion synthesis, incorporating both low-level trajectory and high-level language semantics controls. Specifically, we first train a VQ-VAE to learn a compact latent motion space organized by body parts. We then propose a Masked Trajectories Transformer to make coarse initial predictions of full trajectories of joints based on the learned latent motion space, with user-specified partial trajectories and text descriptions as conditioning. Finally, we introduce an efficient test-time optimization to refine these coarse predictions for accurate trajectory control. Experiments demonstrate that TLControl outperforms the state-of-the-art in trajectory accuracy and time efficiency, making it practical for interactive and high-quality animation generation.
View PDF Chat

DiffusionPhase: Motion Diffusion in Frequency Domain

2023-01-01
Weilin Wan , Yiming Huang , Shutong Wu +4 more
In this study, we introduce a learning-based method for generating high-quality human motion sequences from text descriptions (e.g., ``A person walks forward"). Existing techniques struggle with motion diversity and smooth … In this study, we introduce a learning-based method for generating high-quality human motion sequences from text descriptions (e.g., ``A person walks forward"). Existing techniques struggle with motion diversity and smooth transitions in generating arbitrary-length motion sequences, due to limited text-to-motion datasets and the pose representations used that often lack expressiveness or compactness. To address these issues, we propose the first method for text-conditioned human motion generation in the frequency domain of motions. We develop a network encoder that converts the motion space into a compact yet expressive parameterized phase space with high-frequency details encoded, capturing the local periodicity of motions in time and space with high accuracy. We also introduce a conditional diffusion model for predicting periodic motion parameters based on text descriptions and a start pose, efficiently achieving smooth transitions between motion sequences associated with different text descriptions. Experiments demonstrate that our approach outperforms current methods in generating a broader variety of high-quality motions, and synthesizing long sequences with natural transitions.

Prospective Learning: Principled Extrapolation to the Future

2022-01-01
Joshua T. Vogelstein , Timothy Verstynen , Konrad P. Körding +7 more
Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the assumption that the future … Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the assumption that the future will be identical to the past in distribution or change adversarially. But these assumptions can be either too optimistic or pessimistic for many problems in the real world. Real world scenarios evolve over multiple spatiotemporal scales with partially predictable dynamics. Here we reformulate the learning problem to one that centers around this idea of dynamic futures that are partially learnable. We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning. We argue that prospective learning more accurately characterizes many real world problems that (1) currently stymie existing artificial intelligence solutions and/or (2) lack adequate explanations for how natural intelligences solve them. Thus, studying prospective learning will lead to deeper insights and solutions to currently vexing challenges in both natural and artificial intelligences.

How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression

2022-01-01
Yecheng Jason Ma , Jason Yan , Dinesh Jayaraman +1 more
Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets. We propose $\textbf{Go}$al-conditioned $f$-$\textbf{A}$dvantage $\textbf{R}$egression (GoFAR), a novel regression-based offline … Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets. We propose $\textbf{Go}$al-conditioned $f$-$\textbf{A}$dvantage $\textbf{R}$egression (GoFAR), a novel regression-based offline GCRL algorithm derived from a state-occupancy matching perspective; the key intuition is that the goal-reaching task can be formulated as a state-occupancy matching problem between a dynamics-abiding imitator agent and an expert agent that directly teleports to the goal. In contrast to prior approaches, GoFAR does not require any hindsight relabeling and enjoys uninterleaved optimization for its value and policy networks. These distinct features confer GoFAR with much better offline performance and stability as well as statistical performance guarantee that is unattainable for prior methods. Furthermore, we demonstrate that GoFAR's training objectives can be re-purposed to learn an agent-independent goal-conditioned planner from purely offline source-domain data, which enables zero-shot transfer to new target domains. Through extensive experiments, we validate GoFAR's effectiveness in various problem settings and tasks, significantly outperforming prior state-of-art. Notably, on a real robotic dexterous manipulation task, while no other method makes meaningful progress, GoFAR acquires complex manipulation behavior that successfully accomplishes diverse goals.
View PDF Chat

Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching

2022-01-01
Yecheng Jason Ma , Andrew Shen , Dinesh Jayaraman +1 more
We propose State Matching Offline DIstribution Correction Estimation (SMODICE), a novel and versatile regression-based offline imitation learning (IL) algorithm derived via state-occupancy matching. We show that the SMODICE objective admits … We propose State Matching Offline DIstribution Correction Estimation (SMODICE), a novel and versatile regression-based offline imitation learning (IL) algorithm derived via state-occupancy matching. We show that the SMODICE objective admits a simple optimization procedure through an application of Fenchel duality and an analytic solution in tabular MDPs. Without requiring access to expert actions, SMODICE can be effectively applied to three offline IL settings: (i) imitation from observations (IfO), (ii) IfO with dynamics or morphologically mismatched expert, and (iii) example-based reinforcement learning, which we show can be formulated as a state-occupancy matching problem. We extensively evaluate SMODICE on both gridworld environments as well as on high-dimensional offline benchmarks. Our results demonstrate that SMODICE is effective for all three problem settings and significantly outperforms prior state-of-art.
View PDF Chat

Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming

2022-01-01
Chuan Wen , Jianing Qian , Jierui Lin +3 more
Across applications spanning supervised classification and sequential control, deep learning has been reported to find "shortcut" solutions that fail catastrophically under minor changes in the data distribution. In this paper, … Across applications spanning supervised classification and sequential control, deep learning has been reported to find "shortcut" solutions that fail catastrophically under minor changes in the data distribution. In this paper, we show empirically that DNNs can be coaxed to avoid poor shortcuts by providing an additional "priming" feature computed from key input features, usually a coarse output estimate. Priming relies on approximate domain knowledge of these task-relevant key input features, which is often easy to obtain in practical settings. For example, one might prioritize recent frames over past frames in a video input for visual imitation learning, or salient foreground over background pixels for image classification. On NICO image classification, MuJoCo continuous control, and CARLA autonomous driving, our priming strategy works significantly better than several popular state-of-the-art approaches for feature selection and data augmentation. We connect these empirical findings to recent theoretical results on DNN optimization, and argue theoretically that priming distracts the optimizer away from poor shortcuts by creating better, simpler shortcuts.
View PDF Chat

Vision-based Perimeter Defense via Multiview Pose Estimation

2022-01-01
Elijah S. Lee , Giuseppe Loianno , Dinesh Jayaraman +1 more
Previous studies in the perimeter defense game have largely focused on the fully observable setting where the true player states are known to all players. However, this is unrealistic for … Previous studies in the perimeter defense game have largely focused on the fully observable setting where the true player states are known to all players. However, this is unrealistic for practical implementation since defenders may have to perceive the intruders and estimate their states. In this work, we study the perimeter defense game in a photo-realistic simulator and the real world, requiring defenders to estimate intruder states from vision. We train a deep machine learning-based system for intruder pose detection with domain randomization that aggregates multiple views to reduce state estimation errors and adapt the defensive strategy to account for this. We newly introduce performance metrics to evaluate the vision-based perimeter defense. Through extensive experiments, we show that our approach improves state estimation, and eventually, perimeter defense performance in both 1-defender-vs-1-intruder games, and 2-defenders-vs-1-intruder games.
View PDF Chat

VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training

2022-01-01
Yecheng Jason Ma , Shagun Sodhani , Dinesh Jayaraman +3 more
Reward and representation learning are two long-standing challenges for learning an expanding set of robot manipulation skills from sensory observations. Given the inherent cost and scarcity of in-domain, task-specific robot … Reward and representation learning are two long-standing challenges for learning an expanding set of robot manipulation skills from sensory observations. Given the inherent cost and scarcity of in-domain, task-specific robot data, learning from large, diverse, offline human videos has emerged as a promising path towards acquiring a generally useful visual representation for control; however, how these human videos can be used for general-purpose reward learning remains an open question. We introduce $\textbf{V}$alue-$\textbf{I}$mplicit $\textbf{P}$re-training (VIP), a self-supervised pre-trained visual representation capable of generating dense and smooth reward functions for unseen robotic tasks. VIP casts representation learning from human videos as an offline goal-conditioned reinforcement learning problem and derives a self-supervised dual goal-conditioned value-function objective that does not depend on actions, enabling pre-training on unlabeled human videos. Theoretically, VIP can be understood as a novel implicit time contrastive objective that generates a temporally smooth embedding, enabling the value function to be implicitly defined via the embedding distance, which can then be used to construct the reward for any goal-image specified downstream task. Trained on large-scale Ego4D human videos and without any fine-tuning on in-domain, task-specific data, VIP's frozen representation can provide dense visual reward for an extensive set of simulated and $\textbf{real-robot}$ tasks, enabling diverse reward-based visual control methods and significantly outperforming all prior pre-trained representations. Notably, VIP can enable simple, $\textbf{few-shot}$ offline RL on a suite of real-world robot tasks with as few as 20 trajectories.

Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport

2022-01-01
Sriram Narayanan , Dinesh Jayaraman , Manmohan Chandraker
We address key challenges in long-horizon embodied exploration and navigation by proposing a new object transport task and a novel modular framework for temporally extended navigation. Our first contribution is … We address key challenges in long-horizon embodied exploration and navigation by proposing a new object transport task and a novel modular framework for temporally extended navigation. Our first contribution is the design of a novel Long-HOT environment focused on deep exploration and long-horizon planning where the agent is required to efficiently find and pick up target objects to be carried and dropped at a goal location, with load constraints and optional access to a container if it finds one. Further, we propose a modular hierarchical transport policy (HTP) that builds a topological graph of the scene to perform exploration with the help of weighted frontiers. Our hierarchical approach uses a combination of motion planning algorithms to reach point goals within explored locations and object navigation policies for moving towards semantic targets at unknown locations. Experiments on both our proposed Habitat transport task and on MultiOn benchmarks show that our method significantly outperforms baselines and prior works. Further, we validate the effectiveness of our modular approach for long-horizon transport by demonstrating meaningful generalization to much harder transport scenes with training only on simpler versions of the task.

Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning

2022-01-01
Kun Huang , Edward S. Hu , Dinesh Jayaraman
Physical interactions can often help reveal information that is not readily apparent. For example, we may tug at a table leg to evaluate whether it is built well, or turn … Physical interactions can often help reveal information that is not readily apparent. For example, we may tug at a table leg to evaluate whether it is built well, or turn a water bottle upside down to check that it is watertight. We propose to train robots to acquire such interactive behaviors automatically, for the purpose of evaluating the result of an attempted robotic skill execution. These evaluations in turn serve as "interactive reward functions" (IRFs) for training reinforcement learning policies to perform the target skill, such as screwing the table leg tightly. In addition, even after task policies are fully trained, IRFs can serve as verification mechanisms that improve online task execution. For any given task, our IRFs can be conveniently trained using only examples of successful outcomes, and no further specification is needed to train the task policy thereafter. In our evaluations on door locking and weighted block stacking in simulation, and screw tightening on a real robot, IRFs enable large performance improvements, even outperforming baselines with access to demonstrations or carefully engineered rewards. Project website: https://sites.google.com/view/lirf-corl-2022/
View PDF Chat

Likelihood-Based Diverse Sampling for Trajectory Forecasting

2021-10-01
Yecheng Jason , Jeevana Priya Inala , Dinesh Jayaraman +1 more
Forecasting complex vehicle and pedestrian multi-modal distributions requires powerful probabilistic approaches. Normalizing flows (NF) have recently emerged as an attractive tool to model such distributions. However, a key drawback is … Forecasting complex vehicle and pedestrian multi-modal distributions requires powerful probabilistic approaches. Normalizing flows (NF) have recently emerged as an attractive tool to model such distributions. However, a key drawback is that independent samples drawn from a flow model often do not adequately capture all the modes in the underlying distribution. We propose Likelihood-Based Diverse Sampling (LDS), a method for improving the quality and the diversity of trajectory samples from a pre-trained flow model. Rather than producing individual samples, LDS produces a set of trajectories in one shot. Given a pre-trained forecasting flow model, we train LDS using gradients from the model, to optimize an objective function that rewards high likelihood for individual trajectories in the predicted set, together with high spatial separation among trajectories. LDS outperforms state-of-art post-hoc neural diverse forecasting methods for various pre-trained flow models as well as conditional variational autoencoder (CVAE) models. Crucially, it can also be used for transductive trajectory forecasting, where the diverse forecasts are trained on-the-fly on unlabeled test examples. LDS is easy to implement, and we show that it offers a simple plug-in improvement over baselines on two challenging benchmarks. Code is at: https://github.com/JasonMa2016/LDS
View PDF Chat

Probabilistic Modeling for Human Mesh Recovery

2021-10-01
Nikos Kolotouros , Georgios Pavlakos , Dinesh Jayaraman +1 more
This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and … This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and typically regress a single estimate for a given input. In contrast to that, in this work, we propose to embrace the reconstruction ambiguity and we recast the problem as learning a mapping from the input to a distribution of plausible 3D poses. Our approach is based on the normalizing flows model and offers a series of advantages. For conventional applications, where a single 3D estimate is required, our formulation allows for efficient mode computation. Using the mode leads to performance that is comparable with the state of the art among deterministic unimodal regression models. Simultaneously, since we have access to the likelihood of each sample, we demonstrate that our model is useful in a series of downstream tasks, where we leverage the probabilistic nature of the prediction as a tool for more accurate estimation. These tasks include reconstruction from multiple uncalibrated views, as well as human model fitting, where our model acts as a powerful image-based prior for mesh recovery. Our results validate the importance of probabilistic modeling, and indicate state-of-the-art performance across a variety of settings. Code and models are available at: https://www.seas.upenn.edu/~nkolot/projects/prohmr.
View PDF Chat

Probabilistic Modeling for Human Mesh Recovery.

2021-08-26
Nikos Kolotouros , Georgios Pavlakos , Dinesh Jayaraman +1 more
This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and … This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and typically regress a single estimate for a given input. In contrast to that, in this work, we propose to embrace the reconstruction ambiguity and we recast the problem as learning a mapping from the input to a distribution of plausible 3D poses. Our approach is based on the normalizing flows model and offers a series of advantages. For conventional applications, where a single 3D estimate is required, our formulation allows for efficient mode computation. Using the mode leads to performance that is comparable with the state of the art among deterministic unimodal regression models. Simultaneously, since we have access to the likelihood of each sample, we demonstrate that our model is useful in a series of downstream tasks, where we leverage the probabilistic nature of the prediction as a tool for more accurate estimation. These tasks include reconstruction from multiple uncalibrated views, as well as human model fitting, where our model acts as a powerful image-based prior for mesh recovery. Our results validate the importance of probabilistic modeling, and indicate state-of-the-art performance across a variety of settings. Code and models are available at: this https URL.

Know Thyself: Transferable Visuomotor Control Through Robot-Awareness.

2021-07-19
Edward S. Hu , Kun Huang , Oleh Rybkin +1 more
Training visuomotor robot controllers from scratch on a new robot typically requires generating large amounts of robot-specific data. Could we leverage data previously collected on another robot to reduce or … Training visuomotor robot controllers from scratch on a new robot typically requires generating large amounts of robot-specific data. Could we leverage data previously collected on another robot to reduce or even completely remove this need for robot-specific data? We propose a robot-aware solution paradigm that exploits readily available robot self-knowledge such as proprioception, kinematics, and camera calibration to achieve this. First, we learn modular dynamics models that pair a transferable, robot-agnostic world dynamics module with a robot-specific, analytical robot dynamics module. Next, we set up visual planning costs that draw a distinction between the robot self and the world. Our experiments on tabletop manipulation tasks in simulation and on real robots demonstrate that these plug-in improvements dramatically boost the transferability of visuomotor controllers, even permitting zero-shot transfer onto new robots for the very first time. Project website: this https URL

Conservative Offline Distributional Reinforcement Learning

2021-07-12
Yecheng Jason , Dinesh Jayaraman , Osbert Bastani
Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requires quantifying the … Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requires quantifying the risk associated with different actions. In the online setting, distributional RL algorithms do so by learning the distribution over returns (i.e., cumulative rewards) instead of the expected return; beyond quantifying risk, they have also been shown to learn better representations for planning. We propose Conservative Offline Distributional Actor Critic (CODAC), an offline RL algorithm suitable for both risk-neutral and risk-averse domains. CODAC adapts distributional RL to the offline setting by penalizing the predicted quantiles of the return for out-of-distribution actions. We prove that CODAC learns a conservative return distribution -- in particular, for finite MDPs, CODAC converges to an uniform lower bound on the quantiles of the return distribution; our proof relies on a novel analysis of the distributional Bellman operator. In our experiments, on two challenging robot navigation tasks, CODAC successfully learns risk-averse policies using offline data collected purely from risk-neutral agents. Furthermore, CODAC is state-of-the-art on the D4RL MuJoCo benchmark in terms of both expected and risk-sensitive performance.

An Exploration of Embodied Visual Exploration

2021-02-27
Santhosh Kumar Ramakrishnan , Dinesh Jayaraman , Kristen Grauman
View PDF Chat

How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?

2021-01-01
Jingxi Xu , Bruce Lee , Nikolai Matni +1 more
The difficulty of optimal control problems has classically been characterized in terms of system properties such as minimum eigenvalues of controllability/observability gramians. We revisit these characterizations in the context of … The difficulty of optimal control problems has classically been characterized in terms of system properties such as minimum eigenvalues of controllability/observability gramians. We revisit these characterizations in the context of the increasing popularity of data-driven techniques like reinforcement learning (RL), and in control settings where input observations are high-dimensional images and transition dynamics are unknown. Specifically, we ask: to what extent are quantifiable control and perceptual difficulty metrics of a task predictive of the performance and sample complexity of data-driven controllers? We modulate two different types of partial observability in a cartpole "stick-balancing" problem -- (i) the height of one visible fixation point on the cartpole, which can be used to tune fundamental limits of performance achievable by any controller, and by (ii) the level of perception noise in the fixation point position inferred from depth or RGB images of the cartpole. In these settings, we empirically study two popular families of controllers: RL and system identification-based $H_\infty$ control, using visually estimated system state. Our results show that the fundamental limits of robust control have corresponding implications for the sample-efficiency and performance of learned perception-based controllers. Visit our project website https://jxu.ai/rl-vs-control-web for more information.

Keyframe-Focused Visual Imitation Learning

2021-01-01
Chuan Wen , Jierui Lin , Jianing Qian +2 more
Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better performance for … Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better performance for policies that only access the most recent observation. Recent solutions ranging from causal graph learning to deep information bottlenecks have shown promising results, but failed to scale to realistic settings such as visual imitation. We propose a solution that outperforms these prior approaches by upweighting demonstration keyframes corresponding to expert action changepoints. This simple approach easily scales to complex visual imitation settings. Our experimental results demonstrate consistent performance improvements over all baselines on image-based Gym MuJoCo continuous control tasks. Finally, on the CARLA photorealistic vision-based urban driving simulator, we resolve a long-standing issue in behavioral cloning for driving by demonstrating effective imitation from observation histories. Supplementary materials and code at: \url{https://tinyurl.com/imitation-keyframes}.

How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?

2021-01-01
Jingxi Xu , Bruce Lee , Nikolai Matni +1 more
The difficulty of optimal control problems has classically been characterized in terms of system properties such as minimum eigenvalues of controllability/observability gramians. We revisit these characterizations in the context of … The difficulty of optimal control problems has classically been characterized in terms of system properties such as minimum eigenvalues of controllability/observability gramians. We revisit these characterizations in the context of the increasing popularity of data-driven techniques like reinforcement learning (RL), and in control settings where input observations are high-dimensional images and transition dynamics are unknown. Specifically, we ask: to what extent are quantifiable control and perceptual difficulty metrics of a task predictive of the performance and sample complexity of data-driven controllers? We modulate two different types of partial observability in a cartpole stick-balancing problem -- (i) the height of one visible fixation point on the cartpole, which can be used to tune fundamental limits of performance achievable by any controller, and by (ii) the level of perception noise in the fixation point position inferred from depth or RGB images of the cartpole. In these settings, we empirically study two popular families of controllers: RL and system identification-based $H_\infty$ control, using visually estimated system state. Our results show that the fundamental limits of robust control have corresponding implications for the sample-efficiency and performance of learned perception-based controllers. Visit our project website this https URL for more information.

Probabilistic Modeling for Human Mesh Recovery

2021-01-01
Nikos Kolotouros , Georgios Pavlakos , Dinesh Jayaraman +1 more
This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and … This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and typically regress a single estimate for a given input. In contrast to that, in this work, we propose to embrace the reconstruction ambiguity and we recast the problem as learning a mapping from the input to a distribution of plausible 3D poses. Our approach is based on the normalizing flows model and offers a series of advantages. For conventional applications, where a single 3D estimate is required, our formulation allows for efficient mode computation. Using the mode leads to performance that is comparable with the state of the art among deterministic unimodal regression models. Simultaneously, since we have access to the likelihood of each sample, we demonstrate that our model is useful in a series of downstream tasks, where we leverage the probabilistic nature of the prediction as a tool for more accurate estimation. These tasks include reconstruction from multiple uncalibrated views, as well as human model fitting, where our model acts as a powerful image-based prior for mesh recovery. Our results validate the importance of probabilistic modeling, and indicate state-of-the-art performance across a variety of settings. Code and models are available at: https://www.seas.upenn.edu/~nkolot/projects/prohmr.
View PDF Chat

Know Thyself: Transferable Visual Control Policies Through Robot-Awareness

2021-01-01
Edward S. Hu , Kun Huang , Oleh Rybkin +1 more
Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data. How might we leverage data previously collected on another robot to reduce … Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data. How might we leverage data previously collected on another robot to reduce or even completely remove this need for robot-specific data? We propose a "robot-aware control" paradigm that achieves this by exploiting readily available knowledge about the robot. We then instantiate this in a robot-aware model-based RL policy by training modular dynamics models that couple a transferable, robot-aware world dynamics module with a robot-specific, potentially analytical, robot dynamics module. This also enables us to set up visual planning costs that separately consider the robot agent and the world. Our experiments on tabletop manipulation tasks with simulated and real robots demonstrate that these plug-in improvements dramatically boost the transferability of visual model-based RL policies, even permitting zero-shot transfer of visual manipulation skills onto new robots. Project website: https://www.seas.upenn.edu/~hued/rac
View PDF Chat

Conservative Offline Distributional Reinforcement Learning

2021-01-01
Yecheng Jason Ma , Dinesh Jayaraman , Osbert Bastani
Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requires quantifying the … Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requires quantifying the risk associated with different actions. In the online setting, distributional RL algorithms do so by learning the distribution over returns (i.e., cumulative rewards) instead of the expected return; beyond quantifying risk, they have also been shown to learn better representations for planning. We propose Conservative Offline Distributional Actor Critic (CODAC), an offline RL algorithm suitable for both risk-neutral and risk-averse domains. CODAC adapts distributional RL to the offline setting by penalizing the predicted quantiles of the return for out-of-distribution actions. We prove that CODAC learns a conservative return distribution -- in particular, for finite MDPs, CODAC converges to an uniform lower bound on the quantiles of the return distribution; our proof relies on a novel analysis of the distributional Bellman operator. In our experiments, on two challenging robot navigation tasks, CODAC successfully learns risk-averse policies using offline data collected purely from risk-neutral agents. Furthermore, CODAC is state-of-the-art on the D4RL MuJoCo benchmark in terms of both expected and risk-sensitive performance.
View PDF Chat

Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning

2021-01-01
Yecheng Jason Ma , Andrew Shen , Osbert Bastani +1 more
Reinforcement Learning (RL) agents in the real world must satisfy safety constraints in addition to maximizing a reward objective. Model-based RL algorithms hold promise for reducing unsafe real-world actions: they … Reinforcement Learning (RL) agents in the real world must satisfy safety constraints in addition to maximizing a reward objective. Model-based RL algorithms hold promise for reducing unsafe real-world actions: they may synthesize policies that obey all constraints using simulated samples from a learned model. However, imperfect models can result in real-world constraint violations even for actions that are predicted to satisfy all constraints. We propose Conservative and Adaptive Penalty (CAP), a model-based safe RL framework that accounts for potential modeling errors by capturing model uncertainty and adaptively exploiting it to balance the reward and the cost objectives. First, CAP inflates predicted costs using an uncertainty-based penalty. Theoretically, we show that policies that satisfy this conservative cost constraint are guaranteed to also be feasible in the true environment. We further show that this guarantees the safety of all intermediate solutions during RL training. Further, CAP adaptively tunes this penalty during training using true cost feedback from the environment. We evaluate this conservative and adaptive penalty-based approach for model-based safe RL extensively on state and image-based environments. Our results demonstrate substantial gains in sample-efficiency while incurring fewer violations than prior safe RL algorithms. Code is available at: https://github.com/Redrew/CAP
View PDF Chat

Diverse Sampling for Normalizing Flow Based Trajectory Forecasting.

2020-11-30
Yecheng Jason , Jeevana Priya Inala , Dinesh Jayaraman +1 more
For autonomous cars to drive safely and effectively, they must anticipate the stochastic future trajectories of other agents in the scene, such as pedestrians and other cars. Forecasting such complex … For autonomous cars to drive safely and effectively, they must anticipate the stochastic future trajectories of other agents in the scene, such as pedestrians and other cars. Forecasting such complex multi-modal distributions requires powerful probabilistic approaches. Normalizing flows have recently emerged as an attractive tool to model such distributions. However, when generating trajectory predictions from a flow model, a key drawback is that independent samples often do not adequately capture all the modes in the underlying distribution. We propose Diversity Sampling for Flow (DSF), a method for improving the quality and the diversity of trajectory samples from a pre-trained flow model. Rather than producing individual samples, DSF produces a set of trajectories in one shot. Given a pre-trained forecasting flow model, we train DSF using gradients from the model, to optimize an objective function that rewards high likelihood for individual trajectories in the predicted set, together with high spatial separation between trajectories. DSF is easy to implement, and we show that it offers a simple plug-in improvement for several existing flow-based forecasting models, achieving state-of-art results on two challenging vehicle and pedestrian forecasting benchmarks.
Coauthor Papers Together
Kristen Grauman 26
Osbert Bastani 18
Yecheng Jason Ma 16
Sergey Levine 14
Chelsea Finn 7
Jianing Qian 7
Edward S. Hu 6
Glen Berseth 5
Yecheng Jason 5
William Liang 5
Frederik Ebert 5
Chuan Wen 5
Oleh Rybkin 5
Santhosh Kumar Ramakrishnan 4
Jierui Lin 4
Roberto Calandra 4
Stephen Tian 4
Ruohan Gao 4
Brian Yang 4
Yunshuang Li 4
Alexei A. Efros 4
Eric Eaton 3
Nikos Kolotouros 3
Jeevana Priya Inala 3
Kostas Daniilidis 3
Georgios Pavlakos 3
Hung-Ju Wang 3
Jingxi Xu 3
Yang Gao 3
Daniel Geng 2
Mayur Mudigonda 2
Souradeep Dutta 2
Jesse Zhang 2
Linxi Fan 2
Kun Huang 2
Sriram Narayanan 2
Franziska Meier 2
Bruce Lee 2
Jitendra Malik 2
Manmohan Chandraker 2
Kaustubh Sridhar 2
Neha Das 2
Karl Pertsch 2
Shuran Song 2
Kyle Vedder 2
Luca Weihs 2
Insup Lee 2
Yuke Zhu 2
Akshara Rai 2
Trevor Darrell 2

Deep Residual Learning for Image Recognition

2016-06-01
Kaiming He , Xiangyu Zhang , Shaoqing Ren +1 more
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly … Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers - 8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
View PDF Chat

Learning Image Representations Tied to Ego-Motion

2015-12-01
Dinesh Jayaraman , Kristen Grauman
Understanding how images of objects and scenes behave in response to specific ego-motions is a crucial aspect of proper visual development, yet existing visual learning methods are conspicuously disconnected from … Understanding how images of objects and scenes behave in response to specific ego-motions is a crucial aspect of proper visual development, yet existing visual learning methods are conspicuously disconnected from the physical source of their images. We propose to exploit proprioceptive motor signals to provide unsupervised regularization in convolutional neural networks to learn visual representations from egocentric video. Specifically, we enforce that our learned features exhibit equivariance, i.e, they respond predictably to transformations associated with distinct ego-motions. With three datasets, we show that our unsupervised feature learning approach significantly outperforms previous approaches on visual recognition and next-best-view prediction tasks. In the most challenging test, we show that features learned from video captured on an autonomous driving platform improve large-scale scene recognition in static images from a disjoint domain.
View PDF Chat

Video (language) modeling: a baseline for generative models of natural videos.

2014-12-20
Marc’Aurelio Ranzato , Arthur Szlam , Joan Bruna +3 more
We propose a strong baseline model for unsupervised feature learning using video data. By learning to predict missing frames or extrapolate future frames from an input video sequence, the model … We propose a strong baseline model for unsupervised feature learning using video data. By learning to predict missing frames or extrapolate future frames from an input video sequence, the model discovers both spatial and temporal correlations which are useful to represent complex deformations and motion patterns. The models we propose are largely borrowed from the language modeling literature, and adapted to the vision domain by quantizing the space of image patches into a large dictionary. We demonstrate the approach on both a filling and a generation task. For the first time, we show that, after training on natural videos, such a model can predict non-trivial motions over short video sequences.

ImageNet Large Scale Visual Recognition Challenge

2015-04-10
Olga Russakovsky , Jia Deng , Hao Su +7 more
View PDF Chat

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

2014-06-01
Ross Girshick , Jeff Donahue , Trevor Darrell +1 more
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level … Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.
View PDF Chat

Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video

2016-06-01
Dinesh Jayaraman , Kristen Grauman
How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures … How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact that high-level visual signals change slowly over time, it fails to capture how the visual content changes. We propose to generalize slow feature analysis to "steady" feature analysis. The key idea is to impose a prior that higher order derivatives in the learned feature space must be small. To this end, we train a convolutional neural network with a regularizer on tuples of sequential frames from unlabeled video. It encourages feature changes over time to be smooth, i.e., similar to the most recent changes. Using five diverse datasets, including unlabeled YouTube and KITTI videos, we demonstrate our method's impact on object, scene, and action recognition tasks. We further show that our features learned from unlabeled video can even surpass a standard heavily supervised pretraining approach.
View PDF Chat

3D ShapeNets: A deep representation for volumetric shapes

2015-06-01
Zhirong Wu , Shuran Song , Aditya Khosla +4 more
3D shape is a crucial but heavily underutilized cue in today's computer vision systems, mostly due to the lack of a good generic shape representation. With the recent availability of … 3D shape is a crucial but heavily underutilized cue in today's computer vision systems, mostly due to the lack of a good generic shape representation. With the recent availability of inexpensive 2.5D depth sensors (e.g. Microsoft Kinect), it is becoming increasingly important to have a powerful 3D shape representation in the loop. Apart from category recognition, recovering full 3D shapes from view-based 2.5D depth maps is also a critical part of visual understanding. To this end, we propose to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network. Our model, 3D ShapeNets, learns the distribution of complex 3D shapes across different object categories and arbitrary poses from raw CAD data, and discovers hierarchical compositional part representation automatically. It naturally supports joint object recognition and shape completion from 2.5D depth maps, and it enables active object recognition through view planning. To train our 3D deep learning model, we construct ModelNet - a large-scale 3D CAD model dataset. Extensive experiments show that our 3D deep representation enables significant performance improvement over the-state-of-the-arts in a variety of tasks.
View PDF Chat

Proximal Policy Optimization Algorithms

2017-01-01
John Schulman , Filip Wolski , Prafulla Dhariwal +2 more
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic … We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent. Whereas standard policy gradient methods perform one gradient update per data sample, we propose a novel objective function that enables multiple epochs of minibatch updates. The new methods, which we call proximal policy optimization (PPO), have some of the benefits of trust region policy optimization (TRPO), but they are much simpler to implement, more general, and have better sample complexity (empirically). Our experiments test PPO on a collection of benchmark tasks, including simulated robotic locomotion and Atari game playing, and we show that PPO outperforms other online policy gradient methods, and overall strikes a favorable balance between sample complexity, simplicity, and wall-time.

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction

2016-01-01
Christopher Choy , Danfei Xu , JunYoung Gwak +2 more
View PDF Chat

A dataset for developing and benchmarking active vision

2017-05-01
Phil Ammirato , Patrick Poirson , Eunbyung Park +2 more
We present a new public dataset with a focus on simulating robotic vision tasks in everyday indoor environments using real imagery. The dataset includes 20,000+ RGB-D images and 50,000+ 2D … We present a new public dataset with a focus on simulating robotic vision tasks in everyday indoor environments using real imagery. The dataset includes 20,000+ RGB-D images and 50,000+ 2D bounding boxes of object instances densely captured in 9 unique scenes. We train a fast object category detector for instance detection on our data. Using the dataset we show that, although increasingly accurate and fast, the state of the art for object detection is still severely impacted by object scale, occlusion, and viewing direction all of which matter for robotics applications. We next validate the dataset for simulating active vision, and use the dataset to develop and evaluate a deep-network-based system for next best move prediction for object classification using reinforcement learning. Our dataset is available for download at cs.unc.edu/~ammirato/active_vision_dataset_website/.
View PDF Chat

End to End Learning for Self-Driving Cars

2016-01-01
Mariusz Bojarski , Davide Del Testa , Daniel Dworakowski +7 more
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data … We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system learns to drive in traffic on local roads with or without lane markings and on highways. It also operates in areas with unclear visual guidance such as in parking lots and on unpaved roads. The system automatically learns internal representations of the necessary processing steps such as detecting useful road features with only the human steering angle as the training signal. We never explicitly trained it to detect, for example, the outline of roads. Compared to explicit decomposition of the problem, such as lane marking detection, path planning, and control, our end-to-end system optimizes all processing steps simultaneously. We argue that this will eventually lead to better performance and smaller systems. Better performance will result because the internal components self-optimize to maximize overall system performance, instead of optimizing human-selected intermediate criteria, e.g., lane detection. Such criteria understandably are selected for ease of human interpretation which doesn't automatically guarantee maximum system performance. Smaller networks are possible because the system learns to solve the problem with the minimal number of processing steps. We used an NVIDIA DevBox and Torch 7 for training and an NVIDIA DRIVE(TM) PX self-driving car computer also running Torch 7 for determining where to drive. The system operates at 30 frames per second (FPS).

Understanding image representations by measuring their equivariance and equivalence

2015-06-01
Karel Lenc , Andrea Vedaldi
Despite the importance of image representations such as histograms of oriented gradients and deep Convolutional Neural Networks (CNN), our theoretical understanding of them remains limited. Aiming at filling this gap, … Despite the importance of image representations such as histograms of oriented gradients and deep Convolutional Neural Networks (CNN), our theoretical understanding of them remains limited. Aiming at filling this gap, we investigate three key mathematical properties of representations: equivariance, invariance, and equivalence. Equivariance studies how transformations of the input image are encoded by the representation, invariance being a special case where a transformation has no effect. Equivalence studies whether two representations, for example two different parametrisations of a CNN, capture the same visual information or not. A number of methods to establish these properties empirically are proposed, including introducing transformation and stitching layers in CNNs. These methods are then applied to popular representations to reveal insightful aspects of their structure, including clarifying at which layers in a CNN certain geometric invariances are achieved. While the focus of the paper is theoretical, direct applications to structured-output regression are demonstrated too.
View PDF Chat

An active search strategy for efficient object class detection

2015-06-01
Abel Gonzalez-Garcia , Alexander Vezhnevets , Vittorio Ferrari
Object class detectors typically apply a window classifier to all the windows in a large set, either in a sliding window manner or using object proposals. In this paper, we … Object class detectors typically apply a window classifier to all the windows in a large set, either in a sliding window manner or using object proposals. In this paper, we develop an active search strategy that sequentially chooses the next window to evaluate based on all the information gathered before. This results in a substantial reduction in the number of classifier evaluations and in a more elegant approach in general. Our search strategy is guided by two forces. First, we exploit context as the statistical relation between the appearance of a window and its location relative to the object, as observed in the training set. This enables to jump across distant regions in the image (e.g. observing a sky region suggests that cars might be far below) and is done efficiently in a Random Forest framework. Second, we exploit the score of the classifier to attract the search to promising areas surrounding a highly scored window, and to keep away from areas near low scored ones. Our search strategy can be applied on top of any classifier as it treats it as a black-box. In experiments with R-CNN on the challenging SUN2012 dataset, our method matches the detection accuracy of evaluating all windows independently, while evaluating 9× fewer windows.
View PDF Chat

Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments

2018-06-01
Peter Anderson , Qi Wu , Damien Teney +6 more
A robot that can carry out a natural-language instruction has been a dream since before the Jetsons cartoon series imagined a life of leisure mediated by a fleet of attentive … A robot that can carry out a natural-language instruction has been a dream since before the Jetsons cartoon series imagined a life of leisure mediated by a fleet of attentive robot helpers. It is a dream that remains stubbornly distant. However, recent advances in vision and language methods have made incredible progress in closely related areas. This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering. Both tasks can be interpreted as visually grounded sequence-to-sequence translation problems, and many of the same methods are applicable. To enable and encourage the application of vision and language methods to the problem of interpreting visually-grounded navigation instructions, we present the Matter-port3D Simulator - a large-scale reinforcement learning environment based on real imagery [11]. Using this simulator, which can in future support a range of embodied vision and language tasks, we provide the first benchmark dataset for visually-grounded natural language navigation in real buildings - the Room-to-Room (R2R) dataset1.
View PDF Chat

Very Deep Convolutional Networks for Large-Scale Image Recognition

2014-01-01
Karen Simonyan , Andrew Zisserman
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks … In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Curiosity-driven Exploration by Self-supervised Prediction

2017-05-15
Deepak Pathak , Pulkit Agrawal , Alexei A. Efros +1 more
In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent … In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agent's ability to predict the consequence of its own actions in a visual feature space learned by a self-supervised inverse dynamics model. Our formulation scales to high-dimensional continuous state spaces like images, bypasses the difficulties of directly predicting pixels, and, critically, ignores the aspects of the environment that cannot affect the agent. The proposed approach is evaluated in two environments: VizDoom and Super Mario Bros. Three broad settings are investigated: 1) sparse extrinsic reward, where curiosity allows for far fewer interactions with the environment to reach the goal; 2) exploration with no extrinsic reward, where curiosity pushes the agent to explore more efficiently; and 3) generalization to unseen scenarios (e.g. new levels of the same game) where the knowledge gained from earlier experience helps the agent explore new places much faster than starting from scratch. Demo video and code available at this https URL

Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks

2018-06-01
Dinesh Jayaraman , Kristen Grauman
It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the … It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the problem of learning to look around: if an agent has the ability to voluntarily acquire new views to observe its environment, how can it learn efficient exploratory behaviors to acquire informative visual observations? We propose a reinforcement learning solution, where the agent is rewarded for actions that reduce its uncertainty about the unobserved portions of its environment. Based on this principle, we develop a recurrent neural network-based approach to perform active completion of panoramic natural scenes and 3D object shapes. Crucially, the learned policies are not tied to any recognition task nor to the particular semantic content seen during training. As a result, 1) the learned "look around" behavior is relevant even for new tasks in unseen environments, and 2) training data acquisition involves no manual labeling. Through tests in diverse settings, we demonstrate that our approach learns useful generic policies that transfer to new unseen tasks and environments.
View PDF Chat

More Than a Feeling: Learning to Grasp and Regrasp Using Vision and Touch

2018-07-04
Roberto Calandra , Andrew Owens , Dinesh Jayaraman +5 more
For humans, the process of grasping an object relies heavily on rich tactile feedback. Most recent robotic grasping work, however, has been based only on visual input, and thus cannot … For humans, the process of grasping an object relies heavily on rich tactile feedback. Most recent robotic grasping work, however, has been based only on visual input, and thus cannot easily benefit from feedback after initiating contact. In this letter, we investigate how a robot can learn to use tactile information to iteratively and efficiently adjust its grasp. To this end, we propose an end-to-end action-conditional model that learns regrasping policies from raw visuo-tactile data. This model - a deep, multimodal convolutional network - predicts the outcome of a candidate grasp adjustment, and then executes a grasp by iteratively selecting the most promising actions. Our approach requires neither calibration of the tactile sensors nor any analytical modeling of contact forces, thus reducing the engineering effort required to obtain efficient grasping policies. We train our model with data from about 6450 grasping trials on a two-finger gripper equipped with GelSight high-resolution tactile sensors on each finger. Across extensive experiments, our approach outperforms a variety of baselines at 1) estimating grasp adjustment outcomes, 2) selecting efficient grasp adjustments for quick grasping, and 3) reducing the amount of force applied at the fingers, while maintaining competitive performance. Finally, we study the choices made by our model and show that it has successfully acquired useful and interpretable grasping behaviors.
View PDF Chat

The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?

2017-01-01
Roberto Calandra , Andrew Owens , Manu Upadhyaya +4 more
A successful grasp requires careful balancing of the contact forces. Deducing whether a particular grasp will be successful from indirect measurements, such as vision, is therefore quite challenging, and direct … A successful grasp requires careful balancing of the contact forces. Deducing whether a particular grasp will be successful from indirect measurements, such as vision, is therefore quite challenging, and direct sensing of contacts through touch sensing provides an appealing avenue toward more successful and consistent robotic grasping. However, in order to fully evaluate the value of touch sensing for grasp outcome prediction, we must understand how touch sensing can influence outcome prediction accuracy when combined with other modalities. Doing so using conventional model-based techniques is exceptionally difficult. In this work, we investigate the question of whether touch sensing aids in predicting grasp outcomes within a multimodal sensing framework that combines vision and touch. To that end, we collected more than 9,000 grasping trials using a two-finger gripper equipped with GelSight high-resolution tactile sensors on each finger, and evaluated visuo-tactile deep neural network models to directly predict grasp outcomes from either modality individually, and from both modalities together. Our experimental results indicate that incorporating tactile readings substantially improve grasping performance.

Stochastic Adversarial Video Prediction

2018-04-04
Alex X. Lee , Richard Zhang , Frederik Ebert +3 more
Being able to predict what may happen in the future requires an in-depth understanding of the physical and causal rules that govern the world. A model that is able to … Being able to predict what may happen in the future requires an in-depth understanding of the physical and causal rules that govern the world. A model that is able to do so has a number of appealing applications, from robotic planning to representation learning. However, learning to predict raw future observations, such as frames in a video, is exceedingly challenging -- the ambiguous nature of the problem can cause a naively designed model to average together possible futures into a single, blurry prediction. Recently, this has been addressed by two distinct approaches: (a) latent variational variable models that explicitly model underlying stochasticity and (b) adversarially-trained models that aim to produce naturalistic images. However, a standard latent variable model can struggle to produce realistic results, and a standard adversarially-trained model underutilizes latent variables and fails to produce diverse predictions. We show that these distinct methods are in fact complementary. Combining the two produces predictions that look more realistic to human raters and better cover the range of possible futures. Our method outperforms prior and concurrent work in these aspects.

Deep visual foresight for planning robot motion

2017-05-01
Chelsea Finn , Sergey Levine
A key challenge in scaling up robot learning to many skills and environments is removing the need for human supervision, so that robots can collect their own data and improve … A key challenge in scaling up robot learning to many skills and environments is removing the need for human supervision, so that robots can collect their own data and improve their own performance without being limited by the cost of requesting human feedback. Model-based reinforcement learning holds the promise of enabling an agent to learn to predict the effects of its actions, which could provide flexible predictive models for a wide range of tasks and environments, without detailed human supervision. We develop a method for combining deep action-conditioned video prediction models with model-predictive control that uses entirely unlabeled training data. Our approach does not require a calibrated camera, an instrumented training set-up, nor precise sensing and actuation. Our results show that our method enables a real robot to perform nonprehensile manipulation - pushing objects - and can handle novel objects not seen during training.
View PDF Chat

Unsupervised Visual Representation Learning by Context Prediction

2015-12-01
Carl Doersch , Abhinav Gupta , Alexei A. Efros
This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, … This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image and train a convolutional neural net to predict the position of the second patch relative to the first. We argue that doing well on this task requires the model to learn to recognize objects and their parts. We demonstrate that the feature representation learned using this within-image context indeed captures visual similarity across images. For example, this representation allows us to perform unsupervised visual discovery of objects like cats, people, and even birds from the Pascal VOC 2011 detection dataset. Furthermore, we show that the learned ConvNet can be used in the R-CNN framework [19] and provides a significant boost over a randomly-initialized ConvNet, resulting in state-of-the-art performance among algorithms which use only Pascal-provided training set annotations.
View PDF Chat

Learning to generate chairs with convolutional neural networks

2015-06-01
Alexey Dosovitskiy , Jost Tobias Springenberg , Thomas Brox
We train a generative convolutional neural network which is able to generate images of objects given object type, viewpoint, and color. We train the network in a supervised manner on … We train a generative convolutional neural network which is able to generate images of objects given object type, viewpoint, and color. We train the network in a supervised manner on a dataset of rendered 3D chair models. Our experiments show that the network does not merely learn all images by heart, but rather finds a meaningful representation of a 3D chair model allowing it to assess the similarity of different chairs, interpolate between given viewpoints to generate the missing ones, or invent new chair styles by interpolating between chairs from the training set. We show that the network can be used to find correspondences between different chairs from the dataset, outperforming existing approaches on this task.
View PDF Chat

Multiple Object Recognition with Visual Attention

2014-01-01
Jimmy Ba , Volodymyr Mnih , Koray Kavukcuoglu
We present an attention-based model for recognizing multiple objects in images. The proposed model is a deep recurrent neural network trained with reinforcement learning to attend to the most relevant … We present an attention-based model for recognizing multiple objects in images. The proposed model is a deep recurrent neural network trained with reinforcement learning to attend to the most relevant regions of the input image. We show that the model learns to both localize and recognize multiple objects despite being given only class labels during training. We evaluate the model on the challenging task of transcribing house number sequences from Google Street View images and show that it is both more accurate than the state-of-the-art convolutional networks and uses fewer parameters and less computation.

Deep Stereo: Learning to Predict New Views from the World's Imagery

2016-06-01
John P. Flynn , Ivan Neulander , James Philbin +1 more
Deep networks have recently enjoyed enormous success when applied to recognition and classification problems in computer vision [22, 33], but their use in graphics problems has been limited ([23, 7] … Deep networks have recently enjoyed enormous success when applied to recognition and classification problems in computer vision [22, 33], but their use in graphics problems has been limited ([23, 7] are notable recent exceptions). In this work, we present a novel deep architecture that performs new view synthesis directly from pixels, trained from a large number of posed image sets. In contrast to traditional approaches, which consist of multiple complex stages of processing, each of which requires careful tuning and can fail in unexpected ways, our system is trained end-to-end. The pixels from neighboring views of a scene are presented to the network, which then directly produces the pixels of the unseen view. The benefits of our approach include generality (we only require posed image sets and can easily apply our method to different domains), and high quality results on traditionally difficult scenes. We believe this is due to the end-to-end nature of our system, which is able to plausibly generate pixels according to color, depth, and texture priors learnt automatically from the training data. We show view interpolation results on imagery from the KITTI dataset [12], from data from [1] as well as on Google Street View images. To our knowledge, our work is the first to apply deep learning to the problem of new view synthesis from sets of real-world, natural imagery.
View PDF Chat

Context Encoders: Feature Learning by Inpainting

2016-06-01
Deepak Pathak , Philipp Krähenbühl , Jeff Donahue +2 more
We present an unsupervised visual feature learning algorithm driven by context-based pixel prediction. By analogy with auto-encoders, we propose Context Encoders - a convolutional neural network trained to generate the … We present an unsupervised visual feature learning algorithm driven by context-based pixel prediction. By analogy with auto-encoders, we propose Context Encoders - a convolutional neural network trained to generate the contents of an arbitrary image region conditioned on its surroundings. In order to succeed at this task, context encoders need to both understand the content of the entire image, as well as produce a plausible hypothesis for the missing part(s). When training context encoders, we have experimented with both a standard pixel-wise reconstruction loss, as well as a reconstruction plus an adversarial loss. The latter produces much sharper results because it can better handle multiple modes in the output. We found that a context encoder learns a representation that captures not just appearance but also the semantics of visual structures. We quantitatively demonstrate the effectiveness of our learned features for CNN pre-training on classification, detection, and segmentation tasks. Furthermore, context encoders can be used for semantic inpainting tasks, either stand-alone or as initialization for non-parametric methods.
View PDF Chat

Adam: A Method for Stochastic Optimization

2014-01-01
Diederik P. Kingma , Jimmy Ba
We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has … We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.
View PDF Chat

Dense Optical Flow Prediction from a Static Image

2015-12-01
Jacob Walker , Abhinav Gupta , Martial Hebert
Given a scene, what is going to move, and in what direction will it move? Such a question could be considered a non-semantic form of action prediction. In this work, … Given a scene, what is going to move, and in what direction will it move? Such a question could be considered a non-semantic form of action prediction. In this work, we present a convolutional neural network (CNN) based approach for motion prediction. Given a static image, this CNN predicts the future motion of each and every pixel in the image in terms of optical flow. Our CNN model leverages the data in tens of thousands of realistic videos to train our model. Our method relies on absolutely no human labeling and is able to predict motion based on the context of the scene. Because our CNN model makes no assumptions about the underlying scene, it can predict future optical flow on a diverse set of scenarios. We outperform all previous approaches by large margins.
View PDF Chat

Generative Adversarial Imitation Learning

2016-01-01
Jonathan Ho , Stefano Ermon
Consider learning a policy from example expert behavior, without interaction with the expert or access to reinforcement signal. One approach is to recover the expert's cost function with inverse reinforcement … Consider learning a policy from example expert behavior, without interaction with the expert or access to reinforcement signal. One approach is to recover the expert's cost function with inverse reinforcement learning, then extract a policy from that cost function with reinforcement learning. This approach is indirect and can be slow. We propose a new general framework for directly extracting a policy from data, as if it were obtained by reinforcement learning following inverse reinforcement learning. We show that a certain instantiation of our framework draws an analogy between imitation learning and generative adversarial networks, from which we derive a model-free imitation learning algorithm that obtains significant performance gains over existing model-free methods in imitating complex behaviors in large, high-dimensional environments.

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

2014-01-01
Jun‐Young Chung , Çağlar Gülçehre , Kyunghyun Cho +1 more
In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a … In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gated recurrent unit (GRU). We evaluate these recurrent units on the tasks of polyphonic music modeling and speech signal modeling. Our experiments revealed that these advanced recurrent units are indeed better than more traditional recurrent units such as tanh units. Also, we found GRU to be comparable to LSTM.

Look-Ahead Before You Leap: End-to-End Active Recognition by Forecasting the Effect of Motion

2016-01-01
Dinesh Jayaraman , Kristen Grauman
View PDF Chat

Very Deep Convolutional Networks for Large-Scale Image Recognition

2014-09-04
Karen Simonyan , Andrew Zisserman
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks … In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

2010-01-01
Stéphane Ross , Geoffrey J. Gordon , J. Andrew Bagnell
Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in … Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in theory and often in practice. Some recent approaches provide stronger guarantees in this setting, but remain somewhat unsatisfactory as they train either non-stationary or stochastic policies and require a large number of iterations. In this paper, we propose a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algorithm in an online learning setting. We show that any such no regret algorithm, combined with additional reduction assumptions, must find a policy with good performance under the distribution of observations it induces in such sequential settings. We demonstrate that this new approach outperforms previous approaches on two challenging imitation learning problems and a benchmark sequence labeling problem.

Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks

2019-06-01
Kuan Fang , Alexander Toshev , Li Fei-Fei +1 more
Many robotic applications require the agent to perform long-horizon tasks in partially observable environments. In such applications, decision making at any step can depend on observations received far in the … Many robotic applications require the agent to perform long-horizon tasks in partially observable environments. In such applications, decision making at any step can depend on observations received far in the past. Hence, being able to properly memorize and utilize the long-term history is crucial. In this work, we propose a novel memory-based policy, named Scene Memory Transformer (SMT). The proposed policy embeds and adds each observation to a memory and uses the attention mechanism to exploit spatio-temporal dependencies. This model is generic and can be efficiently trained with reinforcement learning over long episodes. On a range of visual navigation tasks, SMT demonstrates superior performance to existing reactive and memory-based policies by a margin.
View PDF Chat

Target-driven visual navigation in indoor scenes using deep reinforcement learning

2017-05-01
Yuke Zhu , Roozbeh Mottaghi , Eric Kolve +4 more
Two less addressed issues of deep reinforcement learning are (1) lack of generalization capability to new goals, and (2) data inefficiency, i.e., the model requires several (and often costly) episodes … Two less addressed issues of deep reinforcement learning are (1) lack of generalization capability to new goals, and (2) data inefficiency, i.e., the model requires several (and often costly) episodes of trial and error to converge, which makes it impractical to be applied to real-world scenarios. In this paper, we address these two issues and apply our model to target-driven visual navigation. To address the first issue, we propose an actor-critic model whose policy is a function of the goal as well as the current state, which allows better generalization. To address the second issue, we propose the AI2-THOR framework, which provides an environment with high-quality 3D scenes and a physics engine. Our framework enables agents to take actions and interact with objects. Hence, we can collect a huge number of training samples efficiently. We show that our proposed method (1) converges faster than the state-of-the-art deep reinforcement learning methods, (2) generalizes across targets and scenes, (3) generalizes to a real robot scenario with a small amount of fine-tuning (although the model is trained in simulation), (4) is end-to-end trainable and does not need feature engineering, feature matching between frames or 3D reconstruction of the environment.
View PDF Chat

Image-to-Image Translation with Conditional Adversarial Networks

2017-07-01
Phillip Isola , Jun-Yan Zhu , Tinghui Zhou +1 more
We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a … We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Moreover, since the release of the pi×2pi× software associated with this paper, hundreds of twitter users have posted their own artistic experiments using our system. As a community, we no longer hand-engineer our mapping functions, and this work suggests we can achieve reasonable results without handengineering our loss functions either.
View PDF Chat

End-to-End Learning of Action Detection from Frame Glimpses in Videos

2016-06-01
Serena Yeung , Olga Russakovsky , Greg Mori +1 more
In this work we introduce a fully end-to-end approach for action detection in videos that learns to directly predict the temporal bounds of actions. Our intuition is that the process … In this work we introduce a fully end-to-end approach for action detection in videos that learns to directly predict the temporal bounds of actions. Our intuition is that the process of detecting actions is naturally one of observation and refinement: observing moments in video, and refining hypotheses about when an action is occurring. Based on this insight, we formulate our model as a recurrent neural network-based agent that interacts with a video over time. The agent observes video frames and decides both where to look next and when to emit a prediction. Since backpropagation is not adequate in this non-differentiable setting, we use REINFORCE to learn the agent's decision policy. Our model achieves state-of-the-art results on the THUMOS'14 and ActivityNet datasets while observing only a fraction (2% or less) of the video frames.
View PDF Chat

Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision

2016-01-01
Xinchen Yan , Shuicheng Yan , Ersin Yumer +2 more
Understanding the 3D world is a fundamental problem in computer vision. However, learning a good representation of 3D objects is still an open problem due to the high dimensionality of … Understanding the 3D world is a fundamental problem in computer vision. However, learning a good representation of 3D objects is still an open problem due to the high dimensionality of the data and many factors of variation involved. In this work, we investigate the task of single-view 3D object reconstruction from a learning agent's perspective. We formulate the learning process as an interaction between 3D and 2D representations and propose an encoder-decoder network with a novel projection loss defined by the perspective transformation. More importantly, the projection loss enables the unsupervised learning using 2D observation without explicit 3D supervision. We demonstrate the ability of the model in generating 3D volume from a single 2D image with three sets of experiments: (1) learning from single-class objects; (2) learning from multi-class objects and (3) testing on novel object classes. Results show superior performance and better generalization ability for 3D object reconstruction when the projection loss is involved.

Gibson Env: Real-World Perception for Embodied Agents

2018-06-01
Fei Xia , Amir Zamir , Zhiyang He +3 more
Developing visual perception models for active agents and sensorimotor control in the physical world are cumbersome as existing algorithms are too slow to efficiently learn in real-time and robots are … Developing visual perception models for active agents and sensorimotor control in the physical world are cumbersome as existing algorithms are too slow to efficiently learn in real-time and robots are fragile and costly. This has given rise to learning-in-simulation which consequently casts a question on whether the results transfer to real-world. In this paper, we investigate developing real-world perception for active agents, propose Gibson Environment for this purpose, and showcase a set of perceptual tasks learned therein. Gibson is based upon virtualizing real spaces, rather than artificially designed ones, and currently includes over 1400 floor spaces from 572 full buildings. The main characteristics of Gibson are: I. being from the real-world and reflecting its semantic complexity, II. having an internal synthesis mechanism "Goggles" enabling deploying the trained models in real-world without needing domain adaptation, III. embodiment of agents and making them subject to constraints of physics and space.
View PDF Chat

Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments

2011-01-01
Yi Sun , Faustino Gomez , Jürgen Schmidhuber
View PDF Chat

Embodied Question Answering

2018-06-01
Abhishek Das , Samyak Datta , Georgia Gkioxari +3 more
The following topics are dealt with: learning (artificial intelligence); feature extraction; convolutional neural nets; object detection; image segmentation; image classification; computer vision; video signal processing; neural nets; face recognition. The following topics are dealt with: learning (artificial intelligence); feature extraction; convolutional neural nets; object detection; image segmentation; image classification; computer vision; video signal processing; neural nets; face recognition.
View PDF Chat

Sidekick Policy Learning for Active Visual Exploration

2018-01-01
Santhosh Kumar Ramakrishnan , Kristen Grauman
View PDF Chat

Pairwise Decomposition of Image Sequences for Active Multi-view Recognition

2016-06-01
Edward Johns , Stefan Leutenegger , Andrew J. Davison
A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, … A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do not readily embrace recent trends in deep learning. We propose to bring Convolutional Neural Networks to generic multi-view recognition, by decomposing an image sequence into a set of image pairs, classifying each pair independently, and then learning an object classifier by weighting the contribution of each pair. This allows for recognition over arbitrary camera trajectories, without requiring explicit training over the potentially infinite number of camera paths and lengths. Building these pairwise relationships then naturally extends to the next-best-view problem in an active recognition framework. To achieve this, we train a second Convolutional Neural Network to map directly from an observed image to next viewpoint. Finally, we incorporate this into a trajectory optimisation task, whereby the best recognition confidence is sought for a given trajectory length. We present state-of-the-art results in both guided and unguided multi-view recognition on the ModelNet dataset, and show how our method can be used with depth images, greyscale images, or both.
View PDF Chat

Unsupervised Learning of Spatiotemporally Coherent Metrics

2015-12-01
Ross Goroshin , Joan Bruna , Jonathan Tompson +2 more
Current state-of-the-art classification and detection algorithms train deep convolutional networks using labeled data. In this work we study unsupervised feature learning with convolutional networks in the context of temporally coherent … Current state-of-the-art classification and detection algorithms train deep convolutional networks using labeled data. In this work we study unsupervised feature learning with convolutional networks in the context of temporally coherent unlabeled data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity priors. We establish a connection between slow feature learning and metric learning. Using this connection we define "temporal coherence" -- a criterion which can be used to set hyper-parameters in a principled and automated manner. In a transfer learning experiment, we show that the resulting encoder can be used to define a more semantically coherent metric without the use of labels.
View PDF Chat

"Mental Rotation" by Optimizing Transforming Distance

2014-01-01
Wei‐Guang Ding , Graham W. Taylor
The human visual system is able to recognize objects despite transformations that can drastically alter their appearance. To this end, much effort has been devoted to the invariance properties of … The human visual system is able to recognize objects despite transformations that can drastically alter their appearance. To this end, much effort has been devoted to the invariance properties of recognition systems. Invariance can be engineered (e.g. convolutional nets), or learned from data explicitly (e.g. temporal coherence) or implicitly (e.g. by data augmentation). One idea that has not, to date, been explored is the integration of latent variables which permit a search over a learned space of transformations. Motivated by evidence that people mentally simulate transformations in space while comparing examples, so-called "mental rotation", we propose a transforming distance. Here, a trained relational model actively transforms pairs of examples so that they are maximally similar in some feature space yet respect the learned transformational constraints. We apply our method to nearest-neighbour problems on the Toronto Face Database and NORB.

Unsupervised Learning of Visual Representations Using Videos

2015-12-01
Xiaolong Wang , Abhinav Gupta
Is strong supervision necessary for learning a good visual representation? Do we really need millions of semantically-labeled images to train a Convolutional Neural Network (CNN)? In this paper, we present … Is strong supervision necessary for learning a good visual representation? Do we really need millions of semantically-labeled images to train a Convolutional Neural Network (CNN)? In this paper, we present a simple yet surprisingly powerful approach for unsupervised learning of CNN. Specifically, we use hundreds of thousands of unlabeled videos from the web to learn visual representations. Our key idea is that visual tracking provides the supervision. That is, two patches connected by a track should have similar visual representation in deep feature space since they probably belong to same object or object part. We design a Siamese-triplet network with a ranking loss function to train this CNN representation. Without using a single image from ImageNet, just using 100K unlabeled videos and the VOC 2012 dataset, we train an ensemble of unsupervised networks that achieves 52% mAP (no bounding box regression). This performance comes tantalizingly close to its ImageNet-supervised counterpart, an ensemble which achieves a mAP of 54.4%. We also show that our unsupervised network can perform competitively in other tasks such as surface-normal estimation.
View PDF Chat

Anticipating the future by watching unlabeled video.

2015-04-29
Carl Vondrick , Hamed Pirsiavash , Antonio Torralba
In many computer vision applications, machines will need to reason beyond the present, and predict the future. This task is challenging because it requires leveraging extensive commonsense knowledge of the … In many computer vision applications, machines will need to reason beyond the present, and predict the future. This task is challenging because it requires leveraging extensive commonsense knowledge of the world that is difficult to write down. We believe that a promising resource for efficiently obtaining this knowledge is through the massive amounts of readily available unlabeled video. In this paper, we present a large scale framework that capitalizes on temporal structure unlabeled video to learn to anticipate both actions and objects the future. The key idea behind our approach is that we can train deep networks to predict the visual representation of images the future. We experimentally validate this idea on two challenging in the wild video datasets, and our results suggest that learning with unlabeled videos significantly helps forecast actions and anticipate objects.

Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection

2017-06-12
Sergey Levine , Peter Pástor , Alex Krizhevsky +2 more
We describe a learning-based approach to hand-eye coordination for robotic grasping from monocular images. To learn hand-eye coordination for grasping, we trained a large convolutional neural network to predict the … We describe a learning-based approach to hand-eye coordination for robotic grasping from monocular images. To learn hand-eye coordination for grasping, we trained a large convolutional neural network to predict the probability that task-space motion of the gripper will result in successful grasps, using only monocular camera images independent of camera calibration or the current robot pose. This requires the network to observe the spatial relationship between the gripper and objects in the scene, thus learning hand-eye coordination. We then use this network to servo the gripper in real time to achieve successful grasps. We describe two large-scale experiments that we conducted on two separate robotic platforms. In the first experiment, about 800,000 grasp attempts were collected over the course of two months, using between 6 and 14 robotic manipulators at any given time, with differences in camera placement and gripper wear and tear. In the second experiment, we used a different robotic platform and 8 robots to collect a dataset consisting of over 900,000 grasp attempts. The second robotic platform was used to test transfer between robots, and the degree to which data from a different set of robots can be used to aid learning. Our experimental results demonstrate that our approach achieves effective real-time control, can successfully grasp novel objects, and corrects mistakes by continuous servoing. Our transfer experiment also illustrates that data from different robots can be combined to learn more reliable and effective grasping.
View PDF Chat

UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

2012-12-03
Khurram Soomro , Amir Zamir , Mubarak Shah
We introduce UCF101 which is currently the largest dataset of human actions. It consists of 101 action classes, over 13k clips and 27 hours of video data. The database consists … We introduce UCF101 which is currently the largest dataset of human actions. It consists of 101 action classes, over 13k clips and 27 hours of video data. The database consists of realistic user uploaded videos containing camera motion and cluttered background. Additionally, we provide baseline action recognition results on this new dataset using standard bag of words approach with overall performance of 44.5%. To the best of our knowledge, UCF101 is currently the most challenging dataset of actions due to its large number of classes, large number of clips and also unconstrained nature of such clips.

End-to-End Training of Deep Visuomotor Policies

2015-01-01
Sergey Levine , Chelsea Finn , Trevor Darrell +1 more
Policy search methods can allow robots to learn control policies for a wide range of tasks, but practical applications of policy search often require hand-engineered components for perception, state estimation, … Policy search methods can allow robots to learn control policies for a wide range of tasks, but practical applications of policy search often require hand-engineered components for perception, state estimation, and low-level control. In this paper, we aim to answer the following question: does training the perception and control systems jointly end-to-end provide better performance than training each component separately? To this end, we develop a method that can be used to learn policies that map raw image observations directly to torques at the robot's motors. The policies are represented by deep convolutional neural networks (CNNs) with 92,000 parameters, and are trained using a partially observed guided policy search method, which transforms policy search into supervised learning, with supervision provided by a simple trajectory-centric reinforcement learning method. We evaluate our method on a range of real-world manipulation tasks that require close coordination between vision and control, such as screwing a cap onto a bottle, and present simulated comparisons to a range of prior policy search methods.