Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergy

• URL: http://arxiv.org/abs/2210.09435v1
• Date: Mon, 17 Oct 2022 21:12:39 GMT
• Title: Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergy
• Authors: Francesca Bianco and Dimitri Ognibene
• Abstract summary: Theory of Mind (TOM) is the ability to attribute to other agents' beliefs, intentions, or mental states in general. We show the synergy between learning to predict low-level mental states, such as intentions and goals, and attributing high-level ones, such as beliefs. We propose that our architectural approach can be relevant for the design of future adaptive social robots.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: In complex environments, where the human sensory system reaches its limits, our behaviour is strongly driven by our beliefs about the state of the world around us. Accessing others' beliefs, intentions, or mental states in general, could thus allow for more effective social interactions in natural contexts. Yet these variables are not directly observable. Theory of Mind (TOM), the ability to attribute to other agents' beliefs, intentions, or mental states in general, is a crucial feature of human social interaction and has become of interest to the robotics community. Recently, new models that are able to learn TOM have been introduced. In this paper, we show the synergy between learning to predict low-level mental states, such as intentions and goals, and attributing high-level ones, such as beliefs. Assuming that learning of beliefs can take place by observing own decision and beliefs estimation processes in partially observable environments and using a simple feed-forward deep learning model, we show that when learning to predict others' intentions and actions, faster and more accurate predictions can be acquired if beliefs attribution is learnt simultaneously with action and intentions prediction. We show that the learning performance improves even when observing agents with a different decision process and is higher when observing beliefs-driven chunks of behaviour. We propose that our architectural approach can be relevant for the design of future adaptive social robots that should be able to autonomously understand and assist human partners in novel natural environments and tasks.

Related papers

• Learning mental states estimation through self-observation: a developmental synergy between intentions and beliefs representations in a deep-learning model of Theory of Mind [0.35154948148425685]
  Theory of Mind (ToM) is the ability to attribute beliefs, intentions, or mental states to others. We show a developmental synergy between learning to predict low-level mental states and attributing high-level ones. We propose that our computational approach can inform the understanding of human social cognitive development.
  arXiv  Detail & Related papers  (2024-07-25T13:15:25Z)
• Machine Psychology [54.287802134327485]
  We argue that a fruitful direction for research is engaging large language models in behavioral experiments inspired by psychology. We highlight theoretical perspectives, experimental paradigms, and computational analysis techniques that this approach brings to the table. It paves the way for a "machine psychology" for generative artificial intelligence (AI) that goes beyond performance benchmarks.
  arXiv  Detail & Related papers  (2023-03-24T13:24:41Z)
• World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges [51.92834011423463]
  We focus on the two concepts of world models and predictive coding. In neuroscience, predictive coding proposes that the brain continuously predicts its inputs and adapts to model its own dynamics and control behavior in its environment.
  arXiv  Detail & Related papers  (2023-01-14T06:38:14Z)
• Flexible social inference facilitates targeted social learning when rewards are not observable [58.762004496858836]
  Groups coordinate more effectively when individuals are able to learn from others' successes. We suggest that social inference capacities may help bridge this gap, allowing individuals to update their beliefs about others' underlying knowledge and success from observable trajectories of behavior.
  arXiv  Detail & Related papers  (2022-12-01T21:04:03Z)
• Modeling Human Behavior Part I -- Learning and Belief Approaches [0.0]
  We focus on techniques which learn a model or policy of behavior through exploration and feedback. Next generation autonomous and adaptive systems will largely include AI agents and humans working together as teams.
  arXiv  Detail & Related papers  (2022-05-13T07:33:49Z)
• Data-driven emotional body language generation for social robotics [58.88028813371423]
  In social robotics, endowing humanoid robots with the ability to generate bodily expressions of affect can improve human-robot interaction and collaboration. We implement a deep learning data-driven framework that learns from a few hand-designed robotic bodily expressions. The evaluation study found that the anthropomorphism and animacy of the generated expressions are not perceived differently from the hand-designed ones.
  arXiv  Detail & Related papers  (2022-05-02T09:21:39Z)
• Rediscovering Affordance: A Reinforcement Learning Perspective [30.61766085961884]
  We propose an integrative theory of affordance-formation based on the theory of reinforcement learning in cognitive sciences. We implement this theory in a virtual robot model, which demonstrates human-like adaptation of affordance in interactive widgets tasks.
  arXiv  Detail & Related papers  (2021-12-24T00:25:03Z)
• Cognitive architecture aided by working-memory for self-supervised multi-modal humans recognition [54.749127627191655]
  The ability to recognize human partners is an important social skill to build personalized and long-term human-robot interactions. Deep learning networks have achieved state-of-the-art results and demonstrated to be suitable tools to address such a task. One solution is to make robots learn from their first-hand sensory data with self-supervision.
  arXiv  Detail & Related papers  (2021-03-16T13:50:24Z)
• AGENT: A Benchmark for Core Psychological Reasoning [60.35621718321559]
  Intuitive psychology is the ability to reason about hidden mental variables that drive observable actions. Despite recent interest in machine agents that reason about other agents, it is not clear if such agents learn or hold the core psychology principles that drive human reasoning. We present a benchmark consisting of procedurally generated 3D animations, AGENT, structured around four scenarios.
  arXiv  Detail & Related papers  (2021-02-24T14:58:23Z)
• Towards hybrid primary intersubjectivity: a neural robotics library for human science [4.232614032390374]
  We study primary intersubjectivity as a second person perspective experience characterized by predictive engagement. We propose an open-source methodology named textitneural robotics library (NRL) for experimental human-robot interaction. We discuss some ways human-robot (hybrid) intersubjectivity can contribute to human science research.
  arXiv  Detail & Related papers  (2020-06-29T11:35:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.