Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-Critic Reinforcement Learning

doi:10.1109/JAS.2021.1004272

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-Critic Reinforcement Learning
	Ruofan Wu; Zhikai Yao; Jennie Si; He (Helen) Huang
刊名	IEEE/CAA Journal of Automatica Sinica
	2022
卷号	9 期号:1 页码:19-30
关键词	Automatic tracking of intact knee configuration of robotic knee prosthesis direct heuristic dynamic programming (dHDP) reinforcement learning control
ISSN号	2329-9266
DOI	10.1109/JAS.2021.1004272
英文摘要	We address a state-of-the-art reinforcement learning (RL) control approach to automatically configure robotic prosthesis impedance parameters to enable end-to-end, continuous locomotion intended for transfemoral amputee subjects. Specifically, our actor-critic based RL provides tracking control of a robotic knee prosthesis to mimic the intact knee profile. This is a significant advance from our previous RL based automatic tuning of prosthesis control parameters which have centered on regulation control with a designer prescribed robotic knee profile as the target. In addition to presenting the tracking control algorithm based on direct heuristic dynamic programming (dHDP), we provide a control performance guarantee including the case of constrained inputs. We show that our proposed tracking control possesses several important properties, such as weight convergence of the learning networks, Bellman (sub) optimality of the cost-to-go value function and control input, and practical stability of the human-robot system. We further provide a systematic simulation of the proposed tracking control using a realistic human-robot system simulator, the OpenSim, to emulate how the dHDP enables level ground walking, walking on different terrains and at different paces. These results show that our proposed dHDP based tracking control is not only theoretically suitable, but also practically useful.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/45971]
专题	自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	Ruofan Wu,Zhikai Yao,Jennie Si,et al. Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-Critic Reinforcement Learning[J]. IEEE/CAA Journal of Automatica Sinica,2022,9(1):19-30.
APA	Ruofan Wu,Zhikai Yao,Jennie Si,&He .(2022).Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-Critic Reinforcement Learning.IEEE/CAA Journal of Automatica Sinica,9(1),19-30.
MLA	Ruofan Wu,et al."Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-Critic Reinforcement Learning".IEEE/CAA Journal of Automatica Sinica 9.1(2022):19-30.