Theory of Mind Modeling in Search and Rescue Teams

Li, Huao; Oguntola, Ini; Hughes, Dana; Lewis, Michael; Sycara, Katia

doi:10.1109/ro-man53752.2022.9900572

Cited by 3 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current research of empathetic swarm behaviors emerging automatically from broadcast and received signals include [ 37 , 38 ]. Also, the theory of mind is used to model collective behaviors of artificially modeled rescue teams [ 39 , 40 ]. The study by Huang et al [ 41 ] considers a simulated swarm of a few caribou agents to escape from a superior wolf agent.…”

Section: Methodsmentioning

confidence: 99%

Implementation of an Artificially Empathetic Robot Swarm

Siwek,

Żywica,

Siwek

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper presents a novel framework for integrating artificial empathy into robot swarms to improve communication and cooperation. The proposed model uses fuzzy state vectors to represent the knowledge and environment of individual agents, accommodating uncertainties in the real world. By utilizing similarity measures, the model compares states, enabling empathetic reasoning for synchronized swarm behavior. The paper presents a practical application example that demonstrates the efficacy of the model in a robot swarm working toward a common goal. The evaluation methodology involves the open-source physical-based experimentation platform (OPEP), which emphasizes empirical validation in real-world scenarios. The paper proposes a transitional environment that enables automated and repeatable execution of experiments on a swarm of robots using physical devices.

show abstract

Section: Methodsmentioning

confidence: 99%

Implementation of an Artificially Empathetic Robot Swarm

Siwek,

Żywica,

Siwek

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Current research of empathetic swarm behaviours emerging automatically from broadcast and received signals include [34,35]. Also, theory of mind is used to model collective behaviours of artificially modelled rescue teams [36,37]. The study of Huang et.…”

Section: Swarm Applications Also Seem To Open An Opportunity To Effec...mentioning

confidence: 99%

Implementation of an Artificially Empathetic Robot Swarm

Siwek,

Żywica,

Siwek

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper introduces an innovative framework for the integration of artificial empathy into robot swarms to enhance communication and cooperation. The proposed model relies on fuzzy state vectors to represent the knowledge and environment of individual agents, accommodating uncertainties in the real world. Utilizing similarity measures, the model compares states, enabling empathetic reasoning for synchronized swarm behavior. A practical application example demonstrates the model’s efficacy in a robot swarm striving for a common goal. The evaluation methodology involves the Open Source Physical-based Experimentation Platform (OPEP), emphasizing empirical validation in real-world scenarios. The paper proposes a transitional environment that allows automated and repeatable execution of experiments on a swarm of robots using physical devices.

show abstract

“…Theory of Mind, the capacity to reason about others' concealed mental states, is fundamental to human social interactions, collaborations, and communications (Zhang et al, 2012). As LLMs increasingly participate in diverse social interactions with humans, their social intelligence is expected to improve for them to become effective collaborators (Williams et al, 2022;Li et al, 2022). For instance, a proficient AI assistant should be able to infer a human's preferences based on previous experiences without needing to ask.…”

Section: Introductionmentioning

confidence: 99%

Theory of Mind for Multi-Agent Collaboration via Large Language Models

Li,

Chong,

Stepputtis

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

While Large Language Models (LLMs) have demonstrated impressive accomplishments in both reasoning and planning, their abilities in multi-agent collaborations remains largely unexplored.This study evaluates LLMbased agents in a multi-agent cooperative text game with Theory of Mind (ToM) inference tasks, comparing their performance with Multi-Agent Reinforcement Learning (MARL) and planning-based baselines. We observed evidence of emergent collaborative behaviors and high-order Theory of Mind capabilities among LLM-based agents. Our results reveal limitations in LLM-based agents' planning optimization due to systematic failures in managing long-horizon contexts and hallucination about the task state. We explore the use of explicit belief state representations to mitigate these issues, finding that it enhances task performance and the accuracy of ToM inferences for LLMbased agents.

show abstract

Theory of Mind Modeling in Search and Rescue Teams

Cited by 3 publications

References 21 publications

Implementation of an Artificially Empathetic Robot Swarm

Implementation of an Artificially Empathetic Robot Swarm

Implementation of an Artificially Empathetic Robot Swarm

Theory of Mind for Multi-Agent Collaboration via Large Language Models

Contact Info

Product

Resources

About