Cargando…

A Novel Training and Collaboration Integrated Framework for Human–Agent Teleoperation

Human operators have the trend of increasing physical and mental workloads when performing teleoperation tasks in uncertain and dynamic environments. In addition, their performances are influenced by subjective factors, potentially leading to operational errors or task failure. Although agent-based...

Descripción completa

Detalles Bibliográficos
Autores principales: Huang, Zebin, Wang, Ziwei, Bai, Weibang, Huang, Yanpei, Sun, Lichao, Xiao, Bo, Yeatman, Eric M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8708703/
https://www.ncbi.nlm.nih.gov/pubmed/34960435
http://dx.doi.org/10.3390/s21248341
_version_ 1784622751764447232
author Huang, Zebin
Wang, Ziwei
Bai, Weibang
Huang, Yanpei
Sun, Lichao
Xiao, Bo
Yeatman, Eric M.
author_facet Huang, Zebin
Wang, Ziwei
Bai, Weibang
Huang, Yanpei
Sun, Lichao
Xiao, Bo
Yeatman, Eric M.
author_sort Huang, Zebin
collection PubMed
description Human operators have the trend of increasing physical and mental workloads when performing teleoperation tasks in uncertain and dynamic environments. In addition, their performances are influenced by subjective factors, potentially leading to operational errors or task failure. Although agent-based methods offer a promising solution to the above problems, the human experience and intelligence are necessary for teleoperation scenarios. In this paper, a truncated quantile critics reinforcement learning-based integrated framework is proposed for human–agent teleoperation that encompasses training, assessment and agent-based arbitration. The proposed framework allows for an expert training agent, a bilateral training and cooperation process to realize the co-optimization of agent and human. It can provide efficient and quantifiable training feedback. Experiments have been conducted to train subjects with the developed algorithm. The performances of human–human and human–agent cooperation modes are also compared. The results have shown that subjects can complete the tasks of reaching and picking and placing with the assistance of an agent in a shorter operational time, with a higher success rate and less workload than human–human cooperation.
format Online
Article
Text
id pubmed-8708703
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87087032021-12-25 A Novel Training and Collaboration Integrated Framework for Human–Agent Teleoperation Huang, Zebin Wang, Ziwei Bai, Weibang Huang, Yanpei Sun, Lichao Xiao, Bo Yeatman, Eric M. Sensors (Basel) Article Human operators have the trend of increasing physical and mental workloads when performing teleoperation tasks in uncertain and dynamic environments. In addition, their performances are influenced by subjective factors, potentially leading to operational errors or task failure. Although agent-based methods offer a promising solution to the above problems, the human experience and intelligence are necessary for teleoperation scenarios. In this paper, a truncated quantile critics reinforcement learning-based integrated framework is proposed for human–agent teleoperation that encompasses training, assessment and agent-based arbitration. The proposed framework allows for an expert training agent, a bilateral training and cooperation process to realize the co-optimization of agent and human. It can provide efficient and quantifiable training feedback. Experiments have been conducted to train subjects with the developed algorithm. The performances of human–human and human–agent cooperation modes are also compared. The results have shown that subjects can complete the tasks of reaching and picking and placing with the assistance of an agent in a shorter operational time, with a higher success rate and less workload than human–human cooperation. MDPI 2021-12-14 /pmc/articles/PMC8708703/ /pubmed/34960435 http://dx.doi.org/10.3390/s21248341 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Huang, Zebin
Wang, Ziwei
Bai, Weibang
Huang, Yanpei
Sun, Lichao
Xiao, Bo
Yeatman, Eric M.
A Novel Training and Collaboration Integrated Framework for Human–Agent Teleoperation
title A Novel Training and Collaboration Integrated Framework for Human–Agent Teleoperation
title_full A Novel Training and Collaboration Integrated Framework for Human–Agent Teleoperation
title_fullStr A Novel Training and Collaboration Integrated Framework for Human–Agent Teleoperation
title_full_unstemmed A Novel Training and Collaboration Integrated Framework for Human–Agent Teleoperation
title_short A Novel Training and Collaboration Integrated Framework for Human–Agent Teleoperation
title_sort novel training and collaboration integrated framework for human–agent teleoperation
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8708703/
https://www.ncbi.nlm.nih.gov/pubmed/34960435
http://dx.doi.org/10.3390/s21248341
work_keys_str_mv AT huangzebin anoveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT wangziwei anoveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT baiweibang anoveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT huangyanpei anoveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT sunlichao anoveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT xiaobo anoveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT yeatmanericm anoveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT huangzebin noveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT wangziwei noveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT baiweibang noveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT huangyanpei noveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT sunlichao noveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT xiaobo noveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation
AT yeatmanericm noveltrainingandcollaborationintegratedframeworkforhumanagentteleoperation