中文版 | English
Title

Adaptive Environment Modeling Based Reinforcement Learning for Collision Avoidance in Complex Scenes

Author
Corresponding AuthorRui Gao; Qi Hao
DOI
Publication Years
2022
Conference Name
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
ISSN
2153-0858
ISBN
978-1-6654-7928-8
Source Title
Pages
9011-9018
Conference Date
OCT 23-27, 2022
Conference Place
null,Kyoto,JAPAN
Publication Place
345 E 47TH ST, NEW YORK, NY 10017 USA
Publisher
Abstract
The major challenges of collision avoidance for robot navigation in crowded scenes lie in accurate environment modeling, fast perceptions, and trustworthy motion planning policies. This paper presents a novel adaptive environment model based collision avoidance reinforcement learning (i.e., AEMCARL) framework for an unmanned robot to achieve collision-free motions in challenging navigation scenarios. The novelty of this work is threefold: (1) developing a hierarchical network of gated-recurrent-unit (GRU) for environment modeling; (2) developing an adaptive perception mechanism with an attention module; (3) developing an adaptive reward function for the reinforcement learning (RL) framework to jointly train the environment model, perception function and motion planning policy. The proposed method is tested with the Gym-Gazebo simulator and a group of robots (Husky and Turtlebot) under various crowded scenes. Both simulation and experimental results have demonstrated the superior performance of the proposed method over baseline methods.
Keywords
SUSTech Authorship
Corresponding
Language
English
URL[Source Record]
Indexed By
Funding Project
Science and Technology Innovation Committee of Shenzhen City[JCYJ20200109141622964]
WOS Research Area
Automation & Control Systems ; Computer Science ; Engineering ; Robotics
WOS Subject
Automation & Control Systems ; Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Robotics
WOS Accession No
WOS:000909405301088
Data Source
Web of Science
PDF urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9982107
Citation statistics
Cited Times [WOS]:0
Document TypeConference paper
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/415794
DepartmentDepartment of Computer Science and Engineering
工学院
Affiliation
1.Harbin Inst Technol, Harbin, Heilongjiang, Peoples R China
2.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen 518055, Guangdong, Peoples R China
3.Univ Hongkong, Dept Comp Sci, Hong Kong 999077, Peoples R China
4.Southern Univ Sci & Technol, Rsearch Inst Trustworthy Autonomous Syst, Shenzhen, Guangdong, Peoples R China
First Author AffilicationDepartment of Computer Science and Engineering
Corresponding Author AffilicationDepartment of Computer Science and Engineering;  Southern University of Science and Technology
Recommended Citation
GB/T 7714
Shuaijun Wang,Rui Gao,Ruihua Han,et al. Adaptive Environment Modeling Based Reinforcement Learning for Collision Avoidance in Complex Scenes[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2022:9011-9018.
Files in This Item:
File Name/Size DocType Version Access License
69Adaptive Environme(994KB) Restricted Access--
Related Services
Fulltext link
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Shuaijun Wang]'s Articles
[Rui Gao]'s Articles
[Ruihua Han]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Shuaijun Wang]'s Articles
[Rui Gao]'s Articles
[Ruihua Han]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shuaijun Wang]'s Articles
[Rui Gao]'s Articles
[Ruihua Han]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.