Motion optimization for a robotic fish based on adversarial structured control | |
Yan, Shuaizheng2,3; Wang, Jian2,3; Wu, Zhengxing2,3; Yu, Junzhi1,3; Tan, Min2,3 | |
2020-01 | |
会议日期 | 2019年12月6日-2019年12月8日 |
会议地点 | Dali, China |
英文摘要 | This paper proposes a task-based control optimization method for the robotic fish. It is essentially an adversarial structured control consisting of a global control module and a local compensation control module. In detail, the global control module emulates an optimized central pattern generator with Evolutionary Strategy, while the local control module produces targeted compensation control signals with Soft Actor-Critic. The linear summation of two control laws works for the final robotic fish control. Considering that the evolutionary computation optimization algorithms generally have the defect of falling into the local optimum, we propose a method of antagonistic training to improve the optimization performance. The effectiveness of the designed controller is validated by simulation on agents in Mujoco. Noticeably, the simulation results demonstrate that the proposed method teaches the agent fish to move to any target point with a low energy consumption, which lays a good foundation for application of reinforcement learning in real robotic fish control. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/51951] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队 |
通讯作者 | Wu, Zhengxing |
作者单位 | 1.Dept. Mech. Eng. Sci., BIC-ESAT, College of Engineering, Peking University 2.University of Chinese Academy of Sciences 3.State Key Lab Management and Control for Complex Systems, Institute of Automation, CAS |
推荐引用方式 GB/T 7714 | Yan, Shuaizheng,Wang, Jian,Wu, Zhengxing,et al. Motion optimization for a robotic fish based on adversarial structured control[C]. 见:. Dali, China. 2019年12月6日-2019年12月8日. |
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