基于强化学习的仿生机器鱼节能研究

doi:10.13209/j.0479-8023.2019.025

北京大学学报自然科学版 ›› 2019, Vol. 55 ›› Issue (3): 405-410.DOI: 10.13209/j.0479-8023.2019.025

基于强化学习的仿生机器鱼节能研究

付如彬^1,2, 李亮^1,†, 徐成², 谢广明¹

1. 北京大学工学院智能仿生设计实验室, 北京 100871 2. 92453 部队, 福州 350000

收稿日期:2018-05-19 修回日期:2018-10-13 出版日期:2019-05-20 发布日期:2019-05-20
通讯作者: 李亮,E-mail:liatli(at)pku.edu.cn
基金资助:
国家自然科学基金(51575005, 61503008, 61633002, 91648120)和中国博士后科学基金(2015M570013, 2016T90016)资助

Studies on Energy Saving of Robot Fish Based on Reinforcement Learning

FU Rubin^1,2, LI Liang^1,†, XU Cheng², XIE Guangming¹

1. Intelligent Biomimetic Design Lab, College of Engineering, Peking University, Beijing 100871 2. 92453 PLA Troops, Fuzhou 350000

Received:2018-05-19 Revised:2018-10-13 Online:2019-05-20 Published:2019-05-20
Contact: LI Liang,E-mail:liatli(at)pku.edu.cn

摘要/Abstract

摘要：

利用仿生机器鱼平台, 模拟鱼类集群游动过程, 通过实验方法探究机器鱼集群游动时的能量节省问题。具体地, 将两条机器鱼按照一定的前后距离和左右距离固定在低湍流水洞中, 并正对来流方向; 控制前方(领航)机器鱼游动姿态的变化, 使得后方(跟随)机器鱼处在变化的流场环境中。基于强化学习理论, 建立跟随机器鱼在该流场环境下游动所消耗的能量值与其游动姿态之间的映射关系; 利用该映射关系, 获得跟随机器鱼能量消耗最小值对应的游动姿态信息, 并将该信息反馈至机器鱼运动控制器中, 调整机器鱼游动姿态, 达到节省机器鱼能量的目标。

关键词: 仿生机器鱼, 强化学习, 游动姿态, 能量节省

Abstract:

The authors studied energy saving in fish school utilizing a bio-inspired robotic fish platform. Specifically, two robotic fish were fixed in the flow tank against the current with constant left-right distance and front-back distance; the body posture of the front robotic fish was controlled to generate dynamic fluid environments, which would affect the rear robotic fish. Based on reinforcement learning, a relationship was established between energy cost and the body posture of the robotic fish. According to this relationship, the body posture could be acquired which resulted in minimum energy cost for the rear robot. This information was further transferred to the locomotion controller of the robot to adjust its body posture to save most energy.

Key words: robotic fish, reinforcement learning, body posture, energy saving

付如彬, 李亮, 徐成, 谢广明. 基于强化学习的仿生机器鱼节能研究[J]. 北京大学学报自然科学版, 2019, 55(3): 405-410.

FU Rubin, LI Liang, XU Cheng, XIE Guangming. Studies on Energy Saving of Robot Fish Based on Reinforcement Learning[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2019, 55(3): 405-410.

[1]	曲威名, 刘天林, 林惟凯, 罗定生. 机器人学习方法综述[J]. 北京大学学报自然科学版, 2023, 59(6): 1069-1086.
[2]	张领, 曹健, 张袁, 冯硕, 王源. 基于知识蒸馏的脉冲神经网络强化学习方法[J]. 北京大学学报自然科学版, 2023, 59(5): 757-763.

基于强化学习的仿生机器鱼节能研究

Studies on Energy Saving of Robot Fish Based on Reinforcement Learning

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

留言