Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction

During communication, humans express their emotional states using various modalities (e.g., facial expressions and gestures), and they estimate the emotional states of others by paying attention to multimodal signals. To ensure that a communication robot with limited resources can pay attention to s...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Takato Horii, Yukie Nagai
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	active inference. energy based models emotion human-robot interaction multimodal perception Mechanical engineering and machinery TJ1-1570 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/118af9cd56114d168ecc5e032daddd14
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:118af9cd56114d168ecc5e032daddd14
record_format	dspace
spelling	oai:doaj.org-article:118af9cd56114d168ecc5e032daddd142021-12-01T07:20:33ZActive Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction2296-914410.3389/frobt.2021.684401https://doaj.org/article/118af9cd56114d168ecc5e032daddd142021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/frobt.2021.684401/fullhttps://doaj.org/toc/2296-9144During communication, humans express their emotional states using various modalities (e.g., facial expressions and gestures), and they estimate the emotional states of others by paying attention to multimodal signals. To ensure that a communication robot with limited resources can pay attention to such multimodal signals, the main challenge involves selecting the most effective modalities among those expressed. In this study, we propose an active perception method that involves selecting the most informative modalities using a criterion based on energy minimization. This energy-based model can learn the probability of the network state using energy values, whereby a lower energy value represents a higher probability of the state. A multimodal deep belief network, which is an energy-based model, was employed to represent the relationships between the emotional states and multimodal sensory signals. Compared to other active perception methods, the proposed approach demonstrated improved accuracy using limited information in several contexts associated with affective human–robot interaction. We present the differences and advantages of our method compared to other methods through mathematical formulations using, for example, information gain as a criterion. Further, we evaluate performance of our method, as pertains to active inference, which is based on the free energy principle. Consequently, we establish that our method demonstrated superior performance in tasks associated with mutually correlated multimodal information.Takato HoriiTakato HoriiYukie NagaiYukie NagaiFrontiers Media S.A.articleactive inference.energy based modelsemotionhuman-robot interactionmultimodal perceptionMechanical engineering and machineryTJ1-1570Electronic computers. Computer scienceQA75.5-76.95ENFrontiers in Robotics and AI, Vol 8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	active inference. energy based models emotion human-robot interaction multimodal perception Mechanical engineering and machinery TJ1-1570 Electronic computers. Computer science QA75.5-76.95
spellingShingle	active inference. energy based models emotion human-robot interaction multimodal perception Mechanical engineering and machinery TJ1-1570 Electronic computers. Computer science QA75.5-76.95 Takato Horii Takato Horii Yukie Nagai Yukie Nagai Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction
description	During communication, humans express their emotional states using various modalities (e.g., facial expressions and gestures), and they estimate the emotional states of others by paying attention to multimodal signals. To ensure that a communication robot with limited resources can pay attention to such multimodal signals, the main challenge involves selecting the most effective modalities among those expressed. In this study, we propose an active perception method that involves selecting the most informative modalities using a criterion based on energy minimization. This energy-based model can learn the probability of the network state using energy values, whereby a lower energy value represents a higher probability of the state. A multimodal deep belief network, which is an energy-based model, was employed to represent the relationships between the emotional states and multimodal sensory signals. Compared to other active perception methods, the proposed approach demonstrated improved accuracy using limited information in several contexts associated with affective human–robot interaction. We present the differences and advantages of our method compared to other methods through mathematical formulations using, for example, information gain as a criterion. Further, we evaluate performance of our method, as pertains to active inference, which is based on the free energy principle. Consequently, we establish that our method demonstrated superior performance in tasks associated with mutually correlated multimodal information.
format	article
author	Takato Horii Takato Horii Yukie Nagai Yukie Nagai
author_facet	Takato Horii Takato Horii Yukie Nagai Yukie Nagai
author_sort	Takato Horii
title	Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction
title_short	Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction
title_full	Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction
title_fullStr	Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction
title_full_unstemmed	Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction
title_sort	active inference through energy minimization in multimodal affective human–robot interaction
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/118af9cd56114d168ecc5e032daddd14
work_keys_str_mv	AT takatohorii activeinferencethroughenergyminimizationinmultimodalaffectivehumanrobotinteraction AT takatohorii activeinferencethroughenergyminimizationinmultimodalaffectivehumanrobotinteraction AT yukienagai activeinferencethroughenergyminimizationinmultimodalaffectivehumanrobotinteraction AT yukienagai activeinferencethroughenergyminimizationinmultimodalaffectivehumanrobotinteraction
_version_	1718405397108228096

Active Inference Through Energy Minimization in Multimodal Affective Human–Robot Interaction

Ejemplares similares