Full Text:   <204>

CLC number: 

On-line Access: 2022-03-23

Received: 2021-06-14

Revision Accepted: 2022-02-15

Crosschecked: 0000-00-00

Cited: 0

Clicked: 193

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
Open peer comments

Journal of Zhejiang University SCIENCE C 1998 Vol.-1 No.-1 P.

http://doi.org/10.1631/FITEE.2100280


Behavioral control task supervisor with memory based on reinforcement learning for human-multi-robot coordination systems


Author(s):  Jie HUANG, Zhibin MO, Zhenyi ZHANG, Yutao CHEN

Affiliation(s):  School of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, China; more

Corresponding email(s):   yutao.chen@fzu.edu.cn

Key Words:  Human-multi-robot coordination systems, Null-space based behavioral control, Task supervisor, Reinforcement learning, Knowledge base


Share this article to: More |Next Article >>>

Jie HUANG, Zhibin MO, Zhenyi ZHANG, Yutao CHEN. Behavioral control task supervisor with memory based on reinforcement learning for human-multi-robot coordination systems[J]. Frontiers of Information Technology & Electronic Engineering, 1998, -1(-1): .

@article{title="Behavioral control task supervisor with memory based on reinforcement learning for human-multi-robot coordination systems",
author="Jie HUANG, Zhibin MO, Zhenyi ZHANG, Yutao CHEN",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2100280"
}

%0 Journal Article
%T Behavioral control task supervisor with memory based on reinforcement learning for human-multi-robot coordination systems
%A Jie HUANG
%A Zhibin MO
%A Zhenyi ZHANG
%A Yutao CHEN
%J Journal of Zhejiang University SCIENCE C
%V -1
%N -1
%P
%@ 2095-9184
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2100280

TY - JOUR
T1 - Behavioral control task supervisor with memory based on reinforcement learning for human-multi-robot coordination systems
A1 - Jie HUANG
A1 - Zhibin MO
A1 - Zhenyi ZHANG
A1 - Yutao CHEN
J0 - Journal of Zhejiang University Science C
VL - -1
IS - -1
SP -
EP -
%@ 2095-9184
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2100280


Abstract: 
In this paper, a novel reinforcement learning task supervisor (RLTS) with memory a behavioral control framework is proposed for human-multi-robot coordination systems (HMRCSs). The existing HMRCSs are known to suffer from long decision waiting time and large task error caused by repeated human intervention, which restricts the autonomy of multi-robot systems (MRSs). Moreover, existing task supervisors in the the null-space based behavioral control (NSBC) framework need to formulate many priority-switching rules manually, which makes optimal behavioral priority adjustment strategy difficult in the case of multiple robots and multiple tasks. The proposed RLTS with memory provides a detailed integration of the deep-Q-network (DQN) and long-short-term memory (LSTM) knowledge base within the NSBC framework, to achieve an optimal behavioral priority adjustment strategy in the presence of task conflicts, and to reduce the frequency of human intervention. Specifically, the proposed RLTS with memory begins by memorizing the human intervention history when the robot systems were not confident in emergencies, and then reloads the history information when encountering the same situation that has been tackled by humans previously. Simulation results demonstrate the effectiveness of the proposed RLTS. Finally, an experiment using a group of mobile robots subject to external noise and disturbances validates the effectiveness of the proposed RLTS with memory in uncertain real-world environments.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2022 Journal of Zhejiang University-SCIENCE