Cargando…

A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning

Despite the emergence of various human-robot collaboration frameworks, most are not sufficiently flexible to adapt to users with different habits. In this article, a Multimodal Reinforcement Learning Human-Robot Collaboration (MRLC) framework is proposed. It integrates reinforcement learning into hu...

Descripción completa

Detalles Bibliográficos
Autores principales: Cai, Zeyuan, Feng, Zhiquan, Zhou, Liran, Ai, Changsheng, Shao, Haiyan, Yang, Xiaohui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9534615/
https://www.ncbi.nlm.nih.gov/pubmed/36210974
http://dx.doi.org/10.1155/2022/2341898
_version_ 1784802581654011904
author Cai, Zeyuan
Feng, Zhiquan
Zhou, Liran
Ai, Changsheng
Shao, Haiyan
Yang, Xiaohui
author_facet Cai, Zeyuan
Feng, Zhiquan
Zhou, Liran
Ai, Changsheng
Shao, Haiyan
Yang, Xiaohui
author_sort Cai, Zeyuan
collection PubMed
description Despite the emergence of various human-robot collaboration frameworks, most are not sufficiently flexible to adapt to users with different habits. In this article, a Multimodal Reinforcement Learning Human-Robot Collaboration (MRLC) framework is proposed. It integrates reinforcement learning into human-robot collaboration and continuously adapts to the user's habits in the process of collaboration with the user to achieve the effect of human-robot cointegration. With the user's multimodal features as states, the MRLC framework collects the user's speech through natural language processing and employs it to determine the reward of the actions made by the robot. Our experiments demonstrate that the MRLC framework can adapt to the user's habits after repeated learning and better understand the user's intention compared to traditional solutions.
format Online
Article
Text
id pubmed-9534615
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-95346152022-10-06 A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning Cai, Zeyuan Feng, Zhiquan Zhou, Liran Ai, Changsheng Shao, Haiyan Yang, Xiaohui Comput Intell Neurosci Research Article Despite the emergence of various human-robot collaboration frameworks, most are not sufficiently flexible to adapt to users with different habits. In this article, a Multimodal Reinforcement Learning Human-Robot Collaboration (MRLC) framework is proposed. It integrates reinforcement learning into human-robot collaboration and continuously adapts to the user's habits in the process of collaboration with the user to achieve the effect of human-robot cointegration. With the user's multimodal features as states, the MRLC framework collects the user's speech through natural language processing and employs it to determine the reward of the actions made by the robot. Our experiments demonstrate that the MRLC framework can adapt to the user's habits after repeated learning and better understand the user's intention compared to traditional solutions. Hindawi 2022-09-28 /pmc/articles/PMC9534615/ /pubmed/36210974 http://dx.doi.org/10.1155/2022/2341898 Text en Copyright © 2022 Zeyuan Cai et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Cai, Zeyuan
Feng, Zhiquan
Zhou, Liran
Ai, Changsheng
Shao, Haiyan
Yang, Xiaohui
A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning
title A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning
title_full A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning
title_fullStr A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning
title_full_unstemmed A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning
title_short A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning
title_sort framework and algorithm for human-robot collaboration based on multimodal reinforcement learning
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9534615/
https://www.ncbi.nlm.nih.gov/pubmed/36210974
http://dx.doi.org/10.1155/2022/2341898
work_keys_str_mv AT caizeyuan aframeworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning
AT fengzhiquan aframeworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning
AT zhouliran aframeworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning
AT aichangsheng aframeworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning
AT shaohaiyan aframeworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning
AT yangxiaohui aframeworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning
AT caizeyuan frameworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning
AT fengzhiquan frameworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning
AT zhouliran frameworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning
AT aichangsheng frameworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning
AT shaohaiyan frameworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning
AT yangxiaohui frameworkandalgorithmforhumanrobotcollaborationbasedonmultimodalreinforcementlearning