Omnidirectional Drift Control of an Underwater Biomimetic Vehicle-Manipulator System via Reinforcement Learning | |
Ma, Ruichen1,2; Wang, Yu1; Wang, Rui1; Wang, Shuo1,2 | |
2021-05 | |
会议日期 | May 14-16, 2021 |
会议地点 | Suzhou, China |
关键词 | Omnidirectional Drift Control Undulating Fin Underwater Biomimetic Vehicle-manipulator System (UBVMS) Reinforcement Learning Twin Delayed Deep Deterministic policy gradient (TD3) |
DOI | 10.1109/DDCLS52934.2021.9455641 |
英文摘要 | This paper proposes an omnidirectional drift control on an underwater biomimetic vehicle-manipulator system (UBVMS). The UBVMS has two biomimetic propellers, they obtain propulsive force by actuating their undulating fins. A configuration of the system, the dynamics of the UBVMS and the kinematics of the fins are given respectively. Then the control problem is designed as a Markov decision process (MDP). A reinforcement learning method based on the twin delayed deep deterministic policy gradient (TD3) is proposed for this MDP. A control policy is well trained by the reinforcement learning method and tested in eight different simulations. An analysis of the simulation results is also given. |
URL标识 | 查看原文 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/52354] |
专题 | 智能机器人系统研究 |
通讯作者 | Wang, Yu |
作者单位 | 1.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China 2.University of Chinese Academy of Sciences, Beijing 100049, China |
推荐引用方式 GB/T 7714 | Ma, Ruichen,Wang, Yu,Wang, Rui,et al. Omnidirectional Drift Control of an Underwater Biomimetic Vehicle-Manipulator System via Reinforcement Learning[C]. 见:. Suzhou, China. May 14-16, 2021. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论