Cargando…

A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents

Artificial Intelligence (AI) systems are increasingly applied to complex tasks that involve interaction with multiple agents. Such interaction-based systems can lead to safety risks. Due to limited perception and prior knowledge, agents acting in the real world may unconsciously hold false beliefs a...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhao, Zhuoya, Lu, Enmeng, Zhao, Feifei, Zeng, Yi, Zhao, Yuxuan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9050192/
https://www.ncbi.nlm.nih.gov/pubmed/35495023
http://dx.doi.org/10.3389/fnins.2022.753900
_version_ 1784696306787155968
author Zhao, Zhuoya
Lu, Enmeng
Zhao, Feifei
Zeng, Yi
Zhao, Yuxuan
author_facet Zhao, Zhuoya
Lu, Enmeng
Zhao, Feifei
Zeng, Yi
Zhao, Yuxuan
author_sort Zhao, Zhuoya
collection PubMed
description Artificial Intelligence (AI) systems are increasingly applied to complex tasks that involve interaction with multiple agents. Such interaction-based systems can lead to safety risks. Due to limited perception and prior knowledge, agents acting in the real world may unconsciously hold false beliefs and strategies about their environment, leading to safety risks in their future decisions. For humans, we can usually rely on the high-level theory of mind (ToM) capability to perceive the mental states of others, identify risk-inducing errors, and offer our timely help to keep others away from dangerous situations. Inspired by the biological information processing mechanism of ToM, we propose a brain-inspired theory of mind spiking neural network (ToM-SNN) model to enable agents to perceive such risk-inducing errors inside others' mental states and make decisions to help others when necessary. The ToM-SNN model incorporates the multiple brain areas coordination mechanisms and biologically realistic spiking neural networks (SNNs) trained with Reward-modulated Spike-Timing-Dependent Plasticity (R-STDP). To verify the effectiveness of the ToM-SNN model, we conducted various experiments in the gridworld environments with random agents' starting positions and random blocking walls. Experimental results demonstrate that the agent with the ToM-SNN model selects rescue behavior to help others avoid safety risks based on self-experience and prior knowledge. To the best of our knowledge, this study provides a new perspective to explore how agents help others avoid potential risks based on bio-inspired ToM mechanisms and may contribute more inspiration toward better research on safety risks.
format Online
Article
Text
id pubmed-9050192
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-90501922022-04-29 A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents Zhao, Zhuoya Lu, Enmeng Zhao, Feifei Zeng, Yi Zhao, Yuxuan Front Neurosci Neuroscience Artificial Intelligence (AI) systems are increasingly applied to complex tasks that involve interaction with multiple agents. Such interaction-based systems can lead to safety risks. Due to limited perception and prior knowledge, agents acting in the real world may unconsciously hold false beliefs and strategies about their environment, leading to safety risks in their future decisions. For humans, we can usually rely on the high-level theory of mind (ToM) capability to perceive the mental states of others, identify risk-inducing errors, and offer our timely help to keep others away from dangerous situations. Inspired by the biological information processing mechanism of ToM, we propose a brain-inspired theory of mind spiking neural network (ToM-SNN) model to enable agents to perceive such risk-inducing errors inside others' mental states and make decisions to help others when necessary. The ToM-SNN model incorporates the multiple brain areas coordination mechanisms and biologically realistic spiking neural networks (SNNs) trained with Reward-modulated Spike-Timing-Dependent Plasticity (R-STDP). To verify the effectiveness of the ToM-SNN model, we conducted various experiments in the gridworld environments with random agents' starting positions and random blocking walls. Experimental results demonstrate that the agent with the ToM-SNN model selects rescue behavior to help others avoid safety risks based on self-experience and prior knowledge. To the best of our knowledge, this study provides a new perspective to explore how agents help others avoid potential risks based on bio-inspired ToM mechanisms and may contribute more inspiration toward better research on safety risks. Frontiers Media S.A. 2022-04-14 /pmc/articles/PMC9050192/ /pubmed/35495023 http://dx.doi.org/10.3389/fnins.2022.753900 Text en Copyright © 2022 Zhao, Lu, Zhao, Zeng and Zhao. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Zhao, Zhuoya
Lu, Enmeng
Zhao, Feifei
Zeng, Yi
Zhao, Yuxuan
A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents
title A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents
title_full A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents
title_fullStr A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents
title_full_unstemmed A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents
title_short A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents
title_sort brain-inspired theory of mind spiking neural network for reducing safety risks of other agents
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9050192/
https://www.ncbi.nlm.nih.gov/pubmed/35495023
http://dx.doi.org/10.3389/fnins.2022.753900
work_keys_str_mv AT zhaozhuoya abraininspiredtheoryofmindspikingneuralnetworkforreducingsafetyrisksofotheragents
AT luenmeng abraininspiredtheoryofmindspikingneuralnetworkforreducingsafetyrisksofotheragents
AT zhaofeifei abraininspiredtheoryofmindspikingneuralnetworkforreducingsafetyrisksofotheragents
AT zengyi abraininspiredtheoryofmindspikingneuralnetworkforreducingsafetyrisksofotheragents
AT zhaoyuxuan abraininspiredtheoryofmindspikingneuralnetworkforreducingsafetyrisksofotheragents
AT zhaozhuoya braininspiredtheoryofmindspikingneuralnetworkforreducingsafetyrisksofotheragents
AT luenmeng braininspiredtheoryofmindspikingneuralnetworkforreducingsafetyrisksofotheragents
AT zhaofeifei braininspiredtheoryofmindspikingneuralnetworkforreducingsafetyrisksofotheragents
AT zengyi braininspiredtheoryofmindspikingneuralnetworkforreducingsafetyrisksofotheragents
AT zhaoyuxuan braininspiredtheoryofmindspikingneuralnetworkforreducingsafetyrisksofotheragents