中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 中科院工业视觉智能装备工程实验室
  5. 精密感知与控制
Quadrupedal Locomotion in an Energy-efficient Way Based on Reinforcement Learning

文献类型：期刊论文

作者Hao, Tiantian1,2; Xu, De1,2; Yan, Shaohua1,2
刊名INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS
出版日期2024-04-08
页码11
关键词Energy-efficient motion quadruped robot reinforcement learning virtual model control
ISSN号1598-6446
DOI10.1007/s12555-022-1218-x
通讯作者Hao, Tiantian(haotiantian2020@ia.ac.cn)
英文摘要Achieving energy-efficient motion is important for the application of quadruped robots in a wide range. In this paper, we propose a hierarchical control framework that combines reinforcement learning and virtual model control to achieve energy-efficient motion with a planned gait. A reinforcement learning network is designed to learn the policy that maps the state of the robot to the action. The action is the increment of stance ratio, one of the gait parameters. The learned policy network is used as a high-level gait parameter modulator to adjust the gait parameters according to the body's velocity. The virtual model control method is used to compute the required force of robot's body. Then this force is decomposed to the feet of the stance legs with quadratic programming optimization. In the lowest level, the proportional-derivative controllers are used to control the joints' motion. Simulation and experiments are well conducted on the robot A1. The experimental results verify the effectiveness of the proposed method.
WOS关键词ENERGETICS ; GAIT
资助项目Science and Technology Program of Beijing Municipal Science and Technology Commission[Z211100004021021]
WOS研究方向Automation & Control Systems
语种英语
WOS记录号WOS:001198556200003
出版者INST CONTROL ROBOTICS & SYSTEMS, KOREAN INST ELECTRICAL ENGINEERS
资助机构Science and Technology Program of Beijing Municipal Science and Technology Commission
源URL[http://ir.ia.ac.cn/handle/173211/58284]  
专题精密感知与控制研究中心_精密感知与控制
通讯作者Hao, Tiantian
作者单位1.Chinese Acad Sci, Inst Automat, CAS Engn Lab Intelligent Ind Vis, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Hao, Tiantian,Xu, De,Yan, Shaohua. Quadrupedal Locomotion in an Energy-efficient Way Based on Reinforcement Learning[J]. INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS,2024:11.
APA Hao, Tiantian,Xu, De,&Yan, Shaohua.(2024).Quadrupedal Locomotion in an Energy-efficient Way Based on Reinforcement Learning.INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS,11.
MLA Hao, Tiantian,et al."Quadrupedal Locomotion in an Energy-efficient Way Based on Reinforcement Learning".INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS (2024):11.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。