ShanghaiTech University Knowledge Management System
Learning Agile Swimming: An End-to-End Approach without CPGs | |
2025-02 | |
发表期刊 | ARXIV |
ISSN | 2377-3774 |
EISSN | 2377-3766 |
卷号 | 10期号:2页码:1992-1999 |
发表状态 | 已发表 |
DOI | arXiv:2409.10019 |
摘要 | The pursuit of agile and efficient underwater robots, especially bio-mimetic robotic fish, has been impeded by challenges in creating motion controllers that are able to fully exploit their hydrodynamic capabilities. This paper addresses these challenges by introducing a novel, model-free, end-to-end control framework that leverages Deep Reinforcement Learning (DRL) to enable agile and energy-efficient swimming of robotic fish. Unlike existing methods that rely on predefined trigonometric swimming patterns like Central Pattern Generators (CPG), our approach directly outputs low-level actuator commands without strong constraint, enabling the robotic fish to learn agile swimming behaviors. In addition, by integrating a highperformance Computational Fluid Dynamics (CFD) simulator with innovative sim-to-real strategies, such as normalized density matching and servo response matching, the proposed framework significantly mitigates the sim-to-real gap, facilitating direct transfer of control policies to real-world environments without fine-tuning. Comparative experiments demonstrate that our method achieves faster swimming speeds, smaller turning radii, and reduced energy consumption compared to the conventional CPG-PID-based controllers. Furthermore, the proposed framework shows promise in addressing complex tasks in diverse scenario, paving the way for more effective deployment of robotic fish in real aquatic environments. |
关键词 | Robotic fish deep reinforcement learning computational fluid dynamics sim-to-real |
URL | 查看原文 |
收录类别 | EI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[62072310] |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | PPRN:119222069 |
出版者 | Institute of Electrical and Electronics Engineers Inc. |
EI入藏号 | 20250317714762 |
EI主题词 | Reinforcement learning |
EI分类号 | 101.6.1 Robotic Assistants - 1101.2 Machine Learning - 1101.2.1 Deep Learning - 301.1 Fluid Flow - 301.1.3 Aerodynamics (fluid flow) - 651 Aerodynamics - 731.5 Robotics - 731.6 Robot Applications |
原始文献类型 | Journal article (JA) |
来源库 | IEEE |
文献类型 | 期刊论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/464725 |
专题 | 信息科学与技术学院 信息科学与技术学院_PI研究组_刘晓培组 信息科学与技术学院_博士生 信息科学与技术学院_PI研究组_汪阳组 |
通讯作者 | Wang, Yang |
作者单位 | ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China |
第一作者单位 | 信息科学与技术学院 |
通讯作者单位 | 信息科学与技术学院 |
第一作者的第一单位 | 信息科学与技术学院 |
推荐引用方式 GB/T 7714 | Lin, Xiaozhu,Liu, Xiaopei,Wang, Yang. Learning Agile Swimming: An End-to-End Approach without CPGs[J]. ARXIV,2025,10(2):1992-1999. |
APA | Lin, Xiaozhu,Liu, Xiaopei,&Wang, Yang.(2025).Learning Agile Swimming: An End-to-End Approach without CPGs.ARXIV,10(2),1992-1999. |
MLA | Lin, Xiaozhu,et al."Learning Agile Swimming: An End-to-End Approach without CPGs".ARXIV 10.2(2025):1992-1999. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
修改评论
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。