Non-Communication Decentralized Multi-Robot Collision Avoidance in Grid Map Workspace with Double Deep Q-Network
文献类型：期刊论文
| 作者 | Chen, Lin1,2 ; Zhao, Yongting2; Zhao, Huanjun1,2; Zheng, Bin2
|
| 刊名 | SENSORS
 |
| 出版日期 | 2021-02-01 |
| 卷号 | 21期号:3页码:15 |
| 关键词 | robot learning deep reinforcement learning grid map workspace |
| DOI | 10.3390/s21030841 |
| 通讯作者 | Zheng, Bin(zhengbin@cigit.ac.cn) |
| 英文摘要 | This paper presents a novel decentralized multi-robot collision avoidance method with deep reinforcement learning, which is not only suitable for the large-scale grid map workspace multi-robot system, but also directly processes Lidar signals instead of communicating between the robots. According to the particularity of the workspace, we handcrafted a reward function, which considers both the collision avoidance among the robots and as little as possible change of direction of the robots during driving. Using Double Deep Q-Network (DDQN), the policy was trained in the simulation grid map workspace. By designing experiments, we demonstrated that the learned policy can guide the robot well to effectively travel from the initial position to the goal position in the grid map workspace and to avoid collisions with others while driving. |
| 资助项目 | Priority research and design program of Chongqing technology innovation and application demonstration[cstc2017zdcy-zdyfX0036] ; Natural Science Foundation Projects in Chongqing[cstc2019jcyj-msxmX0442] |
| WOS研究方向 | Chemistry ; Engineering ; Instruments & Instrumentation |
| 语种 | 英语 |
| WOS记录号 | WOS:000615487800001 |
| 出版者 | MDPI |
| 源URL | [http://119.78.100.138/handle/2HOD01W0/12922]  |
| 专题 | 中国科学院重庆绿色智能技术研究院 |
| 通讯作者 | Zheng, Bin |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing 400700, Peoples R China |
| 推荐引用方式 GB/T 7714 | Chen, Lin,Zhao, Yongting,Zhao, Huanjun,et al. Non-Communication Decentralized Multi-Robot Collision Avoidance in Grid Map Workspace with Double Deep Q-Network[J]. SENSORS,2021,21(3):15. |
| APA | Chen, Lin,Zhao, Yongting,Zhao, Huanjun,&Zheng, Bin.(2021).Non-Communication Decentralized Multi-Robot Collision Avoidance in Grid Map Workspace with Double Deep Q-Network.SENSORS,21(3),15. |
| MLA | Chen, Lin,et al."Non-Communication Decentralized Multi-Robot Collision Avoidance in Grid Map Workspace with Double Deep Q-Network".SENSORS 21.3(2021):15. |
入库方式： OAI收割
来源：重庆绿色智能技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。