Hierarchical Policy Learning With Demonstration Learning for Robotic Multiple Peg-in-Hole Assembly Tasks

doi:10.1109/TII.2023.3240936

CORC > 自动化研究所 > 中国科学院自动化研究所 > 中科院工业视觉智能装备工程实验室

	Hierarchical Policy Learning With Demonstration Learning for Robotic Multiple Peg-in-Hole Assembly Tasks
	Yan, Shaohua 1,2; Xu, De 1,2; Tao, Xian 1,2
刊名	IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
	2023-10-01
卷号	19 期号:10 页码:10254-10264
关键词	Assembly model demonstration learning (DL) force-based control algorithm hierarchical reinforcement learning (HRL) peg-in-hole assembly
ISSN号	1551-3203
DOI	10.1109/TII.2023.3240936
通讯作者	Xu, De(de.xu@ia.ac.cn)
英文摘要	The force-based control algorithm of robotic multiple peg-in-hole assembly is a challenge. For the difficulty of low adaptability of model-based control algorithms and low learning efficiency of model-free control algorithms, a goal-based hierarchical policy learning (HPL) algorithm that combines conventional control algorithm and demonstration learning (DL) algorithm is proposed to learn the assembly skill. First, the goal-based HPL algorithm adds goal as a new variable to the action value function. Multiple states reached in each episode are randomly selected as subgoals to improve the distribution of positive rewards. Second, an initial policy that combines conventional control algorithm and DL algorithm is designed. The combined coefficient of these two algorithms is learned by HPL algorithm. Finally, a conical surface is used to compute the forces and moments of simplified assembly simulation model. Our algorithm is well implemented in both simulation and real-world environments. The experimental results verify the effectiveness of the proposed method.
资助项目	National Natural Science Foundation of China[62273341] ; Beijing Municipal Natural Science Foundation[4212044] ; Beijing Municipal Natural Science Foundation[TII-22-2698]
WOS关键词	EFFICIENT INSERTION
WOS研究方向	Automation & Control Systems ; Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001047436000028
资助机构	National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54071]
专题	中科院工业视觉智能装备工程实验室
通讯作者	Xu, De
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Yan, Shaohua,Xu, De,Tao, Xian. Hierarchical Policy Learning With Demonstration Learning for Robotic Multiple Peg-in-Hole Assembly Tasks[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,2023,19(10):10254-10264.
APA	Yan, Shaohua,Xu, De,&Tao, Xian.(2023).Hierarchical Policy Learning With Demonstration Learning for Robotic Multiple Peg-in-Hole Assembly Tasks.IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,19(10),10254-10264.
MLA	Yan, Shaohua,et al."Hierarchical Policy Learning With Demonstration Learning for Robotic Multiple Peg-in-Hole Assembly Tasks".IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 19.10(2023):10254-10264.