Computer Science › Artificial Intelligence

AI-based Problem Solving and Planning

Works Count: 36660

Wikipedia

Description

This cluster of papers focuses on artificial intelligence planning and reasoning, covering topics such as planning systems, heuristic search, case-based reasoning, temporal planning, knowledge-based systems, robot control, model-based programming, probabilistic plan recognition, cognitive architecture, and autonomous systems.

Keywords

Planning Systems; Heuristic Search; Case-Based Reasoning; Temporal Planning; Knowledge-Based Systems; Robot Control; Model-Based Programming; Probabilistic Plan Recognition; Cognitive Architecture; Autonomous Systems

Enabling technology for knowledge sharing

1991-09-01

Robert Neches , Richard Fikes , Tim Finin +4 more

Building new knowledge-based systems today usually entails constructing new knowledge bases from scratch. It could instead be done by assembling reusable components. System developers would then only need to worry … Building new knowledge-based systems today usually entails constructing new knowledge bases from scratch. It could instead be done by assembling reusable components. System developers would then only need to worry about creating the specialized knowledge and reasoners new to the specific task of their system. This new system would interoperate with existing systems, using them to perform some of its reasoning. In this way, declarative knowledge, problem- solving techniques, and reasoning services could all be shared among systems. This approach would facilitate building bigger and better systems cheaply. The infrastructure to support such sharing and reuse would lead to greater ubiquity of these systems, potentially transforming the knowledge industry. This article presents a vision of the future in which knowledge-based system development and operation is facilitated by infrastructure and technology for knowledge sharing. It describes an initiative currently under way to develop these ideas and suggests steps that must be taken in the future to try to realize this vision.

The FF Planning System: Fast Plan Generation Through Heuristic Search

2001-05-01

J. Hoffmann , Bernhard Nebel

We describe and evaluate the algorithmic techniques that are used in the FF planning system. Like the HSP system, FF relies on forward state space search, using a heuristic that … We describe and evaluate the algorithmic techniques that are used in the FF planning system. Like the HSP system, FF relies on forward state space search, using a heuristic that estimates goal distances by ignoring delete lists. Unlike HSP's heuristic, our method does not assume facts to be independent. We introduce a novel search strategy that combines hill-climbing with systematic search, and we show how other powerful heuristic information can be extracted and used to prune the search space. FF was the most successful automatic planner at the recent AIPS-2000 planning competition. We review the results of the competition, give data for other benchmark domains, and investigate the reasons for the runtime performance of FF compared to HSP.

View PDF Chat

Rule-Based Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project

1986-01-01

Bruce G. Buchanan , Edward H. Shortliffe

Expert systems: principles and programming

1990-04-01

Joseph C. Giarratano , Gary Riley

From the Publisher: This new edition combines a thorough, balanced treatment of theory and practice with a complete package of CLIPS 6.0 software tools for developing expert systems. It features … From the Publisher: This new edition combines a thorough, balanced treatment of theory and practice with a complete package of CLIPS 6.0 software tools for developing expert systems. It features a balanced blend of expert systems theory and practice; a detailed presentation of CLIPS Version 6.0, a rule-based programming language for expert systems design; and an IBM PC 3 1/2'' disk which contains the complete CLIPS 6.0 executable shell and sample programs for developing expert systems.

Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents

1993-01-01

Ming Tan

An Information-Theoretic Definition of Similarity

1998-07-24

Dekang Lin

Similarity is an important and widely used concept. Previous definitions of similarity are tied to a particular application or a form of knowledge representation. We present an informationtheoretic definition of … Similarity is an important and widely used concept. Previous definitions of similarity are tied to a particular application or a form of knowledge representation. We present an informationtheoretic definition of similarity that is applicable as long as there is a probabilistic model. We demonstrate how our definition can be used to measure the similarity in a number of different domains.

Information Processing and Human-Machine Interaction: An Approach to Cognitive Engineering

1986-09-01

Jens Rasmussen

A model of inexact reasoning in medicine

1975-04-01

Edward H. Shortliffe , Bruce G. Buchanan

Introduction to expert systems

1993-06-01

Peter Jackson

A blackboard architecture for control

1985-07-01

Barbara Hayes‐Roth

The role of fuzzy logic in the management of uncertainty in expert systems

1983-01-01

Lotfi A. Zadeh

Planning in a hierarchy of abstraction spaces

1974-01-01

Earl D. Sacerdoti

An introduction to case-based reasoning

1992-01-01

Janet L. Kolodner

A qualitative physics based on confluences

1984-12-01

Johan de Kleer , John Seely Brown

Learning and executing generalized robot plans

1972-01-01

Richard Fikes , Peter E. Hart , Nils J. Nilsson

Fast planning through planning graph analysis

1997-02-01

Avrim Blum , Merrick L. Furst

GRASP: a search algorithm for propositional satisfiability

1999-05-01

João Marques‐Silva , Karem A. Sakallah

This paper introduces GRASP (Generic seaRch Algorithm for the Satisfiability Problem), a new search algorithm for Propositional Satisfiability (SAT). GRASP incorporates several search-pruning techniques that proved to be quite powerful … This paper introduces GRASP (Generic seaRch Algorithm for the Satisfiability Problem), a new search algorithm for Propositional Satisfiability (SAT). GRASP incorporates several search-pruning techniques that proved to be quite powerful on a wide variety of SAT problems. Some of these techniques are specific to SAT, whereas others are similar in spirit to approaches in other fields of Artificial Intelligence. GRASP is premised on the inevitability of conflicts during the search and its most distinguishing feature is the augmentation of basic backtracking search with a powerful conflict analysis procedure. Analyzing conflicts to determine their causes enables GRASP to backtrack nonchronologically to earlier levels in the search tree, potentially pruning large portions of the search space. In addition, by "recording" the causes of conflicts, GRASP can recognize and preempt the occurrence of similar conflicts later on in the search. Finally, straightforward bookkeeping of the causality chains leading up to conflicts allows GRASP to identify assignments that are necessary for a solution to be found. Experimental results obtained from a large number of benchmarks indicate that application of the proposed conflict analysis techniques to SAT algorithms can be extremely effective for a large number of representative classes of SAT instances.

View PDF Chat

Qualitative process theory

1984-12-01

Kenneth D. Forbus

View PDF Chat

A Cognitive Model of Planning*

1979-10-01

Barbara Hayes‐Roth , Frederick Hayes‐Roth

This paper presents a cognitive model of the planning process. The model generalizes the theoretical architecture of the Hearsay‐ll system. Thus, it assumes that planning comprises the activities of a … This paper presents a cognitive model of the planning process. The model generalizes the theoretical architecture of the Hearsay‐ll system. Thus, it assumes that planning comprises the activities of a variety of cognitive “specialists.” Each specialist can suggest certain kinds of decisions for incorporation into the plan in progress. These include decisions about: (a) how to approach the planning problem; (b) what knowledge bears on the problem; (c) what kinds of actions to try to plan; (d) what specific actions to plan; and (e) how to allocate cognitive resources during planning. Within each of these categories, different specialists suggest decisions at different levels of abstraction. The activities of the various specialists are not coordinated in any systematic way. Instead, the specialists operate opportunistically, suggesting decisions whenever promising opportunities arise. The paper presents a detailed account of the model and illustrates its assumptions with a “thinking aloud” protocol. It also describes the performance of a computer simulation of the model. The paper contrasts the proposed model with successive refinement models and attempts to resolve apparent differences between the two points of view.

View PDF Chat

A theory of diagnosis from first principles

1987-04-01

Raymond Reiter

Expert system methodologies and applications—a decade review from 1995 to 2004

2004-09-14

Shu-Hsien Liao

Planning as heuristic search

2001-06-01

Blai Bonet , Héctor Geffner

View PDF Chat

Readings in Distributed Artificial Intelligence

1988-01-01

Alan H. Bond , Les Gasser

Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches

1994-01-01

Agnar Aamodt , Enric Plaza

Case-based reasoning is a recent approach to problem solving and learning that has got a lot of attention over the last few years. Originating in the US, the basic idea … Case-based reasoning is a recent approach to problem solving and learning that has got a lot of attention over the last few years. Originating in the US, the basic idea and underlying theories have spread to other continents, and we are now within a

A theory and methodology of inductive learning

1983-02-01

Ryszard S. Michalski

Diagnosing multiple faults

1987-04-01

Johan de Kleer , Brian C. Williams

The structure-mapping engine: Algorithm and examples

1989-11-01

Brian Falkenhainer , Kenneth D. Forbus , Dedre Gentner

Artificial Intelligence: A New Synthesis

1998-01-01

Nils J. Nilsson

An assumption-based TMS

1986-03-01

Johan de Kleer

A fuzzy-logic-based approach to qualitative modeling

1993-02-01

Michio Sugeno , Toyoki Yasukawa

This paper discusses a general approach to quali- tative modeling based on fuzzy logic. The method of qualitative modeling is divided into two parts: fuzzy modeling and linguistic approximation. It … This paper discusses a general approach to quali- tative modeling based on fuzzy logic. The method of qualitative modeling is divided into two parts: fuzzy modeling and linguistic approximation. It proposes to use a fuzzy clustering method (fuzzy c-means method) to identify the structure of a fuzzy model. To clarify the advantages of the proposed method, it also shows some examples of modeling, among them a model of a dynamical process and a model of a human operator's control action.

Maintaining knowledge about temporal intervals

1983-11-01

James F. Allen

article Free Access Share on Maintaining knowledge about temporal intervals Author: James F. Allen Univ. of Rochester, Rochester, NY Univ. of Rochester, Rochester, NYView Profile Authors Info & Claims Communications … article Free Access Share on Maintaining knowledge about temporal intervals Author: James F. Allen Univ. of Rochester, Rochester, NY Univ. of Rochester, Rochester, NYView Profile Authors Info & Claims Communications of the ACMVolume 26Issue 11Nov. 1983 pp 832–843https://doi.org/10.1145/182.358434Online:01 November 1983Publication History 5,173citation11,531DownloadsMetricsTotal Citations5,173Total Downloads11,531Last 12 Months644Last 6 weeks101 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my Alerts New Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

View PDF Chat

Plans and situated actions: The problem of human-machine communication

1990-06-01

Philip E. Agre

Planning for conjunctive goals

1987-07-01

David Chapman

View PDF Chat

SOAR: An architecture for general intelligence

1987-09-01

John E. Laird , Allen Newell , Paul S. Rosenbloom

View PDF Chat

Qualitative simulation

1986-09-01

Benjamin Kuipers

The Geometry of Random Fields.

1982-12-01

Lawrence Gray , Robert J. Adler

Extremes and Related Properties of Random Sequences and Processes.

1985-03-01

Richard A. Davis , M. R. Leadbetter , Georg Lindgren +1 more

View PDF Chat

Heuristics: Intelligent Search Strategies for Computer Problem Solving

1986-01-01

The Fast Downward Planning System

2006-07-12

Malte Helmert

Fast Downward is a classical planning system based on heuristic search. It can deal with general deterministic planning problems encoded in the propositional fragment of PDDL2.2, including advanced features like … Fast Downward is a classical planning system based on heuristic search. It can deal with general deterministic planning problems encoded in the propositional fragment of PDDL2.2, including advanced features like ADL conditions and effects and derived predicates (axioms). Like other well-known planners such as HSP and FF, Fast Downward is a progression planner, searching the space of world states of a planning task in the forward direction. However, unlike other PDDL planning systems, Fast Downward does not use the propositional PDDL representation of a planning task directly. Instead, the input is first translated into an alternative representation called multi-valued planning tasks, which makes many of the implicit constraints of a propositional planning task explicit. Exploiting this alternative representation, Fast Downward uses hierarchical decompositions of planning tasks for computing its heuristic function, called the causal graph heuristic, which is very different from traditional HSP-like heuristics based on ignoring negative interactions of operators. In this article, we give a full account of Fast Downwards approach to solving multi-valued planning tasks. We extend our earlier discussion of the causal graph heuristic to tasks involving axioms and conditional effects and present some novel techniques for search control that are used within Fast Downwards best-first search algorithm: preferred operators transfer the idea of helpful actions from local search to global best-first search, deferred evaluation of heuristic functions mitigates the negative effect of large branching factors on search performance, and multi-heuristic best-first search combines several heuristic evaluation functions within a single search algorithm in an orthogonal way. We also describe efficient data structures for fast state expansion (successor generators and axiom evaluators) and present a new non-heuristic search algorithm called focused iterative-broadening search, which utilizes the information encoded in causal graphs in a novel way. Fast Downward has proven remarkably successful: It won the "classical (i.e., propositional, non-optimising) track of the 4th International Planning Competition at ICAPS 2004, following in the footsteps of planners such as FF and LPG. Our experiments show that it also performs very well on the benchmarks of the earlier planning competitions and provide some insights about the usefulness of the new search enhancements.

View PDF Chat

Induction of decision trees

1986-03-01

J. R. Quinlan

View PDF Chat

Cognitive systems engineering

1995-01-01

Integration of Generative AI with Human Expertise in HEOR: A Hybrid Intelligence Framework

2025-06-25

Tushar Srivastava , H. Irfan , V.V. Babiy +1 more | Advances in Therapy

Health economics and outcomes research (HEOR) is pivotal in shaping healthcare policies, optimizing decision-making, and ensuring effective resource allocation. However, current HEOR workflows often struggle to keep pace with the … Health economics and outcomes research (HEOR) is pivotal in shaping healthcare policies, optimizing decision-making, and ensuring effective resource allocation. However, current HEOR workflows often struggle to keep pace with the growing complexity of data, constrained resources, and the need for adaptable, real-time analysis. Generative artificial intelligence (Gen-AI) offers a transformative opportunity to address these challenges by augmenting human expertise with advanced computational capabilities. Despite its potential, the integration of Gen-AI into HEOR workflows remains largely unexplored, leaving professionals uncertain about how to effectively leverage its capabilities. This study bridges this gap by introducing a novel hybrid intelligence framework that integrates Gen-AI with human input to enhance critical HEOR tasks, including health economic model conceptualization, evidence synthesis, and patient-reported outcome (PRO) assessment. Building on established adoption theories such as the technology acceptance model (TAM) and unified theory of acceptance and use of technology (UTAUT), the framework emphasizes key enablers like perceived usefulness, ease of use, organizational readiness, and social influence to support seamless integration within HEOR workflows. The framework incorporates two implementable approaches: human-in-the-loop (HITL), where AI takes the lead with human validation and refinement, and AI-in-the-loop (AITL), where human professionals remain in control, leveraging AI for verification and enhancements. Advanced tools like retrieval augmented generation (RAG) and Graph RAG are employed alongside techniques such as prompt engineering to ensure outputs are reliable, contextually grounded, and aligned with HEOR needs. By combining computational efficiency with human insight, this hybrid approach contributes to the evolving integration of AI in HEOR, fostering innovation and driving actionable outcomes. This research sets a foundation for practically integrating Gen-AI into HEOR, offering an actionable pathway to transform workflows, improve healthcare decision-making, and ultimately enhance patient care.

Topology-aware planning under linear temporal logic constraints

2025-06-23

Dan P. Guralnik , Yu Wang , Warren E. Dixon | Journal of Applied and Computational Topology

Robot manipulation in everyday activities with the CRAM 2.0 cognitive architecture and generalized action plans

2025-06-21

Michael Beetz , Gayane Kazhoyan , David Vernon | Cognitive Systems Research

Towards an Effective Prompting With AI Systems: The Jujitsu Framework

2025-06-13

Anurag Jain , Zaiyong Tang , Anil Gurung | Journal of Applied Business and Economics

As Large Language Models (LLMs) become central to AI applications, prompt engineering has emerged as a critical skill for optimizing model output. However, existing prompting techniques lack a solid theoretical … As Large Language Models (LLMs) become central to AI applications, prompt engineering has emerged as a critical skill for optimizing model output. However, existing prompting techniques lack a solid theoretical foundation and continue to exhibit persistent limitations, such as insufficient objectivity and inadequate awareness of training data. We present a Framework that offers a principled model for prompt engineering, aligning with both the core mechanisms of LLMs and the principles of objective communication. This framework addresses critical gaps in existing methods and provides a systematic, transferable approach to prompt design. By working with - rather than against – the LLM architecture, the framework enhances accuracy, interpretability, and versatility across domains, thereby advancing the evolving landscape of human-AI interaction.

A Bio-Inspired Goal-Directed Cognitive Map Approach to Robot Navigation and Mapping

2025-06-08

Matthew Hicks , Tingjun Lei , Chaomin Luo +2 more | 2022 IEEE Congress on Evolutionary Computation (CEC)

From NPCs to AI Assistants

2025-06-06

Mahmoud Hamash , Hanan Ghreir , Peter Tiernan +1 more | Advances in computational intelligence and robotics book series

The integration of Artificial Intelligence (AI)-driven agents, including Non-Player Characters (NPCs), pedagogical agents, and AI assistants, within Immersive Virtual Reality (IVR) environments represents a rapidly evolving domain in educational technology. … The integration of Artificial Intelligence (AI)-driven agents, including Non-Player Characters (NPCs), pedagogical agents, and AI assistants, within Immersive Virtual Reality (IVR) environments represents a rapidly evolving domain in educational technology. This chapter conducts a scoping review (2015–2025) following the PRISMA for Scoping Reviews (PRISMA-ScR) guidelines to synthesize existing research on AI-driven agents in STEM (Science, Technology, Engineering, and Mathematics) education. A systematic search across Scopus, ScienceDirect, and ERIC identified 82 publications, with only three meeting the eligibility criteria. The review maps the current state of research, highlights knowledge gaps, and suggests future directions for educators, researchers, and policymakers. The findings underscore the limited but growing body of literature on AI-driven agents in immersive STEM education, emphasizing the need for further empirical investigations to explore their impact on engagement, learning outcomes, and instructional practices.

Developing Effective CORE Teams and Operations

2025-06-05

Michael Gary , David L. Heiber , Ivory A. Toldson | BRILL eBooks

Performance benchmarking of multimodal data-driven approaches in industrial settings

2025-06-01

Diyar Altinses , Andreas Schwung | Machine Learning with Applications

Conflict Management in a Distance to Prototype-Based Evidential Neural Network

2025-06-01

Dănuţ-Vasile Giurgi , Mihreteab Negash Geletu , Thomas Laurain +3 more | International Journal of Approximate Reasoning

Multimodal AI Architectures: Integrating Vision and Language for Enhanced Scene Understanding

2025-05-31

Mohammed A. Al Ghamdi | International Journal of Multidisciplinary Research in Science, Engineering and Technology.

The integration of vision and language has emerged as a transformative frontier in artificial intelligence, enabling systems to achieve human-like comprehension of complex scenes by synthesizing multimodal data. This paper … The integration of vision and language has emerged as a transformative frontier in artificial intelligence, enabling systems to achieve human-like comprehension of complex scenes by synthesizing multimodal data. This paper explores cutting-edge advancements in multimodal architectures, focusing on their ability to bridge visual and linguistic modalities for tasks such as visual question answering (VQA), image captioning, and cross-modal retrieval. A key innovation lies in two-stage vision processing, where hierarchical visual features are preserved through intermediate layer outputs and fused with language models via strategically placed cross-attention mechanisms. For instance, Meta’s MLLaMA employs a 32-layer vision encoder followed by an 8-layer global encoder with gated attention, concatenating multi-scale features to enrich visual representations. Recent trends highlight the prominence of transformer-based frameworks and joint embedding spaces, as seen in models like CLIP and Flamingo, which leverage contrastive learning to align text and image semantics. These architectures enable zero-shot generalization, outperforming taskspecific models in novel domains. Meanwhile, graph neural networks (GNNs) are gaining traction for modeling nonEuclidean relationships in multimodal data, particularly in medical imaging and robotics. Fusion techniques remain central to multimodal integration, with early, late, and hybrid approaches balancing computational efficiency and deep modality interaction. Cross-modal attention mechanisms, as in the Meshed-Memory Transformer (\(M^2\)), enhance image captioning by dynamically weighting visual and textual features.

ASCOmind: Is instant ASCO abstract analysis possible with AI agents?

2025-05-28

Kyeryoung Lee , Hunki Paek , Nneka Ofoegbu +3 more | Journal of Clinical Oncology

7557 Background: The ASCO Annual Meeting receives thousands of abstracts annually on ongoing therapies. Extracting actionable insights from this large volume of data through manual review is time-consuming. To reduce … 7557 Background: The ASCO Annual Meeting receives thousands of abstracts annually on ongoing therapies. Extracting actionable insights from this large volume of data through manual review is time-consuming. To reduce manual workload and accelerate evidence synthesis, we implemented an AI-Agent system to assess the feasibility of deploying AI agents for efficient, large-scale data analysis and insight generation. Methods: GPT4o-based ASCOmind was designed with a robust framework of six autonomous and collaborative AI agents: Pre-processor, Categorizer, MetadataExtractor, Analyzer, Visualizer, and ProtocolMaker to systematically generate and visualize insights from ASCO abstracts. We demonstrate and evaluate ASCOmind by applying it to 2024 multiple myeloma (MM) studies. Using human reviewers as the gold standard, we assessed the quality and efficiency of the system focusing on outcome data accuracy, visualized charts, and workflow recipes documentations. Results: ASCOmind processed abstracts in the plasma cell dyscrasia section, categorizing 60 MM abstracts into 26 clinical trials and 34 as real-world studies. Manual abstraction of 51 predefined data elements required >60 mins/abstract, whereas ASCOmind completed the same task in <5min/article. The ASCOmind not only significantly reduced the processing time but also instantly analyzed and visualized the extracted data within 10 min. For instance, 27 included high-risk populations with cytogenetic abnormalities (n=20), extramedullary disease (n=7), or elderly patients (n=4). Across 51 interventional studies, 33 targeted relapsed/refractory MM (RRMM) and 18 focused on newly diagnosed MM (NDMM). ASCOmind generated a treatment distribution table for RRMM and NDMM (Table 1), with one misclassification corrected by humans-Mezigdomide reclassified from ADC to the correct category. Additionally, granular efficacy/safety outcome values and summarized study findings were also successfully extracted and visualized. Conclusions: Our preliminary analysis of ASCOmind demonstrated high accuracy and efficiency in automating abstract analysis, enabling rapid analysis of trends and outcomes. This feasibility study highlights the scalability of AI systems across all cancer types, supporting decision-making. Treatment distribution in RRMM and NDMM studies. Total (N=51) Therapy Category Examples No. of Studies % RRMM(N=33) BCMA-CAR-T Therapies Cilta-cel, Ide-cel, ARI0002h 8 24.3% BCMA-Bispecific Ab Therapies Teclistamab, Talquetamab, Elranatamab, Linvoseltamab, ABBV-383 16 48.5% ADC Belantamab mafodotin, Elotuzumab, 5 15.2% Cereblon E3 Ligase Modulator Mezigdomide, Iberdomide, 2 6.0% Others OriCAR017, Venetoclax 2 6.0% NDMM(N=18) Triplet/Quadruplet SOC VRd, Isa-VRd 8 44.5% Transplantation ASCT, Tandem Transplantation 6 33.3% ADC Belantamab mafodotin, 2 11.1% BCMA-Directed Therapies Cilta-cel + Lenalidomide, Teclistamab 2 11.1%

Bellman-optimal Decisions and Expert Intuition

2025-05-28

Ilia Atanasov , George Mengov , Anton Gerunov | Proceedings of the Bulgarian Academy of Sciences

Engineers and other professionals believe in rationality and seek to make optimal choices most of the time. Their expert intuition is developed over years of education and practice, enhanced by … Engineers and other professionals believe in rationality and seek to make optimal choices most of the time. Their expert intuition is developed over years of education and practice, enhanced by various decision-support tools. Yet being human, they are prone to emotional biases leading away from the best judgement and action. Here we report statistically significant deviations from the Bellman optimality principle by participants in a lab experiment about managing an abstract production system. We find that when the supply of a key resource diminishes and people are surrounded by others in the same position, they perform below a weak form of the Bellman-optimal criterion. In contrast, one's choices become much more successful when additional expert information is made available.

Paradigm Change in AI

2025-05-28

Yixin Zhong | WORLD SCIENTIFIC eBooks

Mars Explorer Experiments: Ideas from Data Mining Point of View

2025-05-27

Mohammed Ali Mohammed , Nadhim Azeez Sayel , Nidaa A. Abbas

In the context of the "Mars Explorer Experiments," a set of autonomous agents (vehicles) must navigate an unknown, obstacle-filled terrain to locate and collect rock samples, with limited communication between … In the context of the "Mars Explorer Experiments," a set of autonomous agents (vehicles) must navigate an unknown, obstacle-filled terrain to locate and collect rock samples, with limited communication between agents and no prior detailed map of the planet. This paper explores the application of data mining techniques in the development of autonomous vehicle control architectures for Mars exploration, specifically focused on the task of collecting precious rock samples according to three types of agents (Cooperative Agents, Non-Cooperative Agents, Subsumption Architecture ) through describing the agent with the data mining point of view (problem statement in agent, solution using data mining algorithms, discussion problem and solution from data mining point of view). A significant portion of the paper discusses how data mining approaches such as clustering, reinforcement learning, anomaly detection, and pattern mining can be employed to improve agent coordination, exploration strategies, and real-time decision-making in dynamic and uncertain environments. Incorporating data mining algorithms into 'Mars exploration experiments' shows a hopeful way to boost the performance and decision-making abilities of autonomous agents on Mars. The paper shows that the data mining algorithms are not just beneficial but essential in developing intelligent, cooperative, and autonomous systems for Mars exploration vehicles.

10 Bias in Cybernetic AI Systems

2025-05-27

Closed-Loop Multistep Planning

2025-05-23

Giulia Lafratta , Bernd Porr , Christopher Chandler +1 more

Abstract Living organisms interact with their surroundings in a closed-loop fashion, where sensory inputs dictate the initiation and termination of behaviors. Even simple animals are able to develop and execute … Abstract Living organisms interact with their surroundings in a closed-loop fashion, where sensory inputs dictate the initiation and termination of behaviors. Even simple animals are able to develop and execute complex plans, which has not yet been replicated in robotics using pure closed-loop input control. We propose a solution to this problem by defining a set of discrete and temporary closed-loop controllers, called “Tasks,” each representing a closed-loop behavior. We further introduce a supervisory module that has an innate understanding of physics and causality, through which it can simulate the execution of Task sequences over time and store the results in a model of the environment. On the basis of this model, plans can be made by chaining temporary closed-loop controllers. Our proposed framework was implemented for a robot and tested in two scenarios as proof of concept.

View PDF Chat

On the Combination of Classical Knowledge Engineering Tools and LLMs to Build Automated Planning Models

2025-05-22

Alba Gragera , Ángel García‐Olaya , Fernando Fernández

Planning with Nondeterministic Models

2025-05-19

Planning with Probabilistic Models

2025-05-19

Planning with Deterministic Models

2025-05-19

PRefLexOR: preference-based recursive language modeling for exploratory optimization of reasoning and agentic thinking

2025-05-14

Markus J. Buehler

View PDF Chat

Hierarchical Plan Repair via Plan Recognition and Plan Correction

2025-05-14

Kristýna Pantůčková , Roman Barták

Hierarchical planning extends classical planning by introducing a hierarchy of tasks describing how tasks decompose into subtasks until primitive tasks -- actions -- forming a plan are obtained. Plan repair … Hierarchical planning extends classical planning by introducing a hierarchy of tasks describing how tasks decompose into subtasks until primitive tasks -- actions -- forming a plan are obtained. Plan repair deals with plans that failed to execute due to a sudden state change. In particular, plan repair modifies the not-yet executed suffix of the plan to achieve the original goal. Hierarchical plan repair aims to modify a partially executed plan while respecting the task hierarchy. This paper describes how hierarchical plan repair can be realized by solving closely related hierarchical plan recognition and correction problems.

AI vs. Human Programmers: Complexity and Performance in Code Generation

2025-05-10

Samina Azeem , Muhammad Shumail Naveed , Muhammad Sajid +1 more

Large language models, such as ChatGPT, have demonstrated the capability to perform diverse tasks across various domains, significantly enhancing efficiency. However, their growing adoption raises concerns about potential job displacement, … Large language models, such as ChatGPT, have demonstrated the capability to perform diverse tasks across various domains, significantly enhancing efficiency. However, their growing adoption raises concerns about potential job displacement, especially in technical fields. While numerous studies have explored the performance of large language models in technical domains, a notable gap exists in evaluating their capabilities in programming. This study addresses that gap by comparing ChatGPT (GPT-4) with human experts in the programming domain to assess whether ChatGPT has reached a level where it could replace human programmers. To achieve this objective, the study generated 300 Python programs using ChatGPT (GPT-4) and compared them with functionally equivalent programs developed by three experienced human programmers. The evaluation encompassed both quantitative and qualitative analyses, employing metrics such as Halstead Complexity, Cyclomatic Complexity, and expert judgment from two human evaluators. The findings revealed statistically significant differences between ChatGPT generated and human-written code. Programs generated by ChatGPT exhibited verbosity, complexity, and resource demands, as evidenced by higher program volume, difficulty, and cyclomatic complexity scores. In qualitative terms, ChatGPT’s code was more readable but lagged in key areas, including documentation quality, function structuring, and adherence to coding standards. Conversely, human-written programs excelled in maintainability, error handling, and addressing edge cases. Although ChatGPT demonstrated remarkable efficiency in generating functional code, its output required extensive review and refinement to meet standards. The study concluded while ChatGPT serves as valuable tool for code generation, it has not yet reached the level required to replace human expertise in programming.

Artificial Intelligence (AI) to Trace the Pathways of MPs

2025-05-09

Madhulika Bhati , Joydeep Biswas , Saurav Kumar +1 more

AI Applications in Talent Acquisition and Retention

2025-05-07

Mohsin Shaikh

The use of AI based resume screening in making the talent acquisition processes more efficient and fairer. Through the capabilities of the HireVue platform that combines NLP and ML, resumes … The use of AI based resume screening in making the talent acquisition processes more efficient and fairer. Through the capabilities of the HireVue platform that combines NLP and ML, resumes are picked apart systematically and examined to match candidate qualifications towards the requirements of chosen job. It reduces greatly manual screening time and provides means to identify high potential by looking into skills, experience and (potential) fit with the culture. Through reducing presence of human bias and automating repetitive process, HireVue improves recruiter productivity while also enhancing the candidate experience. This paper describes how AI-driven screening has been deployed by a mid-sized technology firm and provides an evaluation of its impact against the key KPOs of time to hire, quality of candidates and diversity outcome. This shows the advantages of have AI based resume screening to not only serve as an efficient hiring, but also go with data based decisions in secondary especially in view of the scalability and adpatability in various industries in search of implementing efficient process of talent getting.

Neural schema architecture for the robots and the advancements

2025-05-06

Saksham Shivasish , Shailendra Singh

There are no module or modifier tropes

2025-05-02

Markku Keinänen