| |||||||
ShanghaiTech University Knowledge Management System
Multi-Modal Legged Locomotion Framework with Automated Residual Reinforcement Learning | |
2022-10-01 | |
发表期刊 | IEEE ROBOTICS AND AUTOMATION LETTERS (IF:4.6[JCR-2023],5.5[5-Year]) |
ISSN | 2377-3766 |
EISSN | 2377-3766 |
卷号 | 7期号:4页码:1-8 |
发表状态 | 已发表 |
DOI | 10.1109/LRA.2022.3191071 |
摘要 | While quadruped robots usually have good stability and load capacity, bipedal robots offer a higher level of flexibility / adaptability to different tasks and environments. A multi-modal legged robot can take the best of both worlds. In this paper, we propose a multi-modal locomotion framework that is composed of a hand-crafted transition motion and a learning-based bipedal controllerlearnt by a novel algorithm called Automated Residual Reinforcement Learning. This framework aims to endow arbitrary quadruped robots with the ability to walk bipedally. In particular, we 1) design an additional supporting structure for a quadruped robot and a sequential multi-modal transition strategy; 2) propose a novel class of Reinforcement Learning algorithms for bipedal control and evaluate their performances in both simulation and the real world. Experimental results show that our proposed algorithms have the best performance in simulation and maintain a good performance in a real-world robot. Overall, our multi-modal robot could successfully switch between biped and quadruped, and walk in both modes. Experiment videos and code are available at https://chenaah.github.io/multimodal/. IEEE |
关键词 | Anthropomorphic robots Biped locomotion Learning algorithms Machine design Multipurpose robots Evolutionary robotics Hip Humanoid robot Knee Legged locomotion Legged robots Multi-modal locomotion Quadrupedal robot Reinforcement learnings |
URL | 查看原文 |
收录类别 | SCI ; SCIE ; EI |
语种 | 英语 |
WOS研究方向 | Robotics |
WOS类目 | Robotics |
WOS记录号 | WOS:000835813000063 |
出版者 | Institute of Electrical and Electronics Engineers Inc. |
EI入藏号 | 20223112529851 |
EI主题词 | Reinforcement learning |
EI分类号 | 461.3 Biomechanics, Bionics and Biomimetics ; 601 Mechanical Design ; 723.4 Artificial Intelligence ; 723.4.2 Machine Learning ; 731.5 Robotics ; 731.6 Robot Applications |
原始文献类型 | Article in Press |
来源库 | IEEE |
引用统计 | 正在获取...
|
文献类型 | 期刊论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/211747 |
专题 | 信息科学与技术学院 信息科学与技术学院_PI研究组_ANDRE LUIS MACEDO ROSENDO SILVA组 信息科学与技术学院_硕士生 |
作者单位 | School of Information Science and Technology, ShanghaiTech University, Shanghai, China |
第一作者单位 | 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 | Chen Yu,Andre Rosendo. Multi-Modal Legged Locomotion Framework with Automated Residual Reinforcement Learning[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2022,7(4):1-8. |
APA | Chen Yu,&Andre Rosendo.(2022).Multi-Modal Legged Locomotion Framework with Automated Residual Reinforcement Learning.IEEE ROBOTICS AND AUTOMATION LETTERS,7(4),1-8. |
MLA | Chen Yu,et al."Multi-Modal Legged Locomotion Framework with Automated Residual Reinforcement Learning".IEEE ROBOTICS AND AUTOMATION LETTERS 7.4(2022):1-8. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
个性服务 |
查看访问统计 |
谷歌学术 |
谷歌学术中相似的文章 |
[Chen Yu]的文章 |
[Andre Rosendo]的文章 |
百度学术 |
百度学术中相似的文章 |
[Chen Yu]的文章 |
[Andre Rosendo]的文章 |
必应学术 |
必应学术中相似的文章 |
[Chen Yu]的文章 |
[Andre Rosendo]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。