Visual behavior modelling for robotic theory of mind

Abstract Behavior modeling is an essential cognitive ability that underlies many aspects of human and animal social behavior (Watson in Psychol Rev 20:158, 1913), and an ability we would like to endow robots. Most studies of machine behavior modelling, however, rely on symbolic or selected parametri...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Boyuan Chen, Carl Vondrick, Hod Lipson
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/cd7a91c276d741a38635cc2a85203743
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:cd7a91c276d741a38635cc2a85203743
record_format dspace
spelling oai:doaj.org-article:cd7a91c276d741a38635cc2a852037432021-12-02T14:12:47ZVisual behavior modelling for robotic theory of mind10.1038/s41598-020-77918-x2045-2322https://doaj.org/article/cd7a91c276d741a38635cc2a852037432021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-77918-xhttps://doaj.org/toc/2045-2322Abstract Behavior modeling is an essential cognitive ability that underlies many aspects of human and animal social behavior (Watson in Psychol Rev 20:158, 1913), and an ability we would like to endow robots. Most studies of machine behavior modelling, however, rely on symbolic or selected parametric sensory inputs and built-in knowledge relevant to a given task. Here, we propose that an observer can model the behavior of an actor through visual processing alone, without any prior symbolic information and assumptions about relevant inputs. To test this hypothesis, we designed a non-verbal non-symbolic robotic experiment in which an observer must visualize future plans of an actor robot, based only on an image depicting the initial scene of the actor robot. We found that an AI-observer is able to visualize the future plans of the actor with 98.5% success across four different activities, even when the activity is not known a-priori. We hypothesize that such visual behavior modeling is an essential cognitive ability that will allow machines to understand and coordinate with surrounding agents, while sidestepping the notorious symbol grounding problem. Through a false-belief test, we suggest that this approach may be a precursor to Theory of Mind, one of the distinguishing hallmarks of primate social cognition.Boyuan ChenCarl VondrickHod LipsonNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Boyuan Chen
Carl Vondrick
Hod Lipson
Visual behavior modelling for robotic theory of mind
description Abstract Behavior modeling is an essential cognitive ability that underlies many aspects of human and animal social behavior (Watson in Psychol Rev 20:158, 1913), and an ability we would like to endow robots. Most studies of machine behavior modelling, however, rely on symbolic or selected parametric sensory inputs and built-in knowledge relevant to a given task. Here, we propose that an observer can model the behavior of an actor through visual processing alone, without any prior symbolic information and assumptions about relevant inputs. To test this hypothesis, we designed a non-verbal non-symbolic robotic experiment in which an observer must visualize future plans of an actor robot, based only on an image depicting the initial scene of the actor robot. We found that an AI-observer is able to visualize the future plans of the actor with 98.5% success across four different activities, even when the activity is not known a-priori. We hypothesize that such visual behavior modeling is an essential cognitive ability that will allow machines to understand and coordinate with surrounding agents, while sidestepping the notorious symbol grounding problem. Through a false-belief test, we suggest that this approach may be a precursor to Theory of Mind, one of the distinguishing hallmarks of primate social cognition.
format article
author Boyuan Chen
Carl Vondrick
Hod Lipson
author_facet Boyuan Chen
Carl Vondrick
Hod Lipson
author_sort Boyuan Chen
title Visual behavior modelling for robotic theory of mind
title_short Visual behavior modelling for robotic theory of mind
title_full Visual behavior modelling for robotic theory of mind
title_fullStr Visual behavior modelling for robotic theory of mind
title_full_unstemmed Visual behavior modelling for robotic theory of mind
title_sort visual behavior modelling for robotic theory of mind
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/cd7a91c276d741a38635cc2a85203743
work_keys_str_mv AT boyuanchen visualbehaviormodellingforrobotictheoryofmind
AT carlvondrick visualbehaviormodellingforrobotictheoryofmind
AT hodlipson visualbehaviormodellingforrobotictheoryofmind
_version_ 1718391750543802368