CASOG: Conservative Actor&#x2013;Critic With SmOoth Gradient for Skill Learning in Robot-Assisted Intervention

doi:10.1109/TIE.2023.3310021

	CASOG: Conservative Actor–Critic With SmOoth Gradient for Skill Learning in Robot-Assisted Intervention
	Li, Hao 1,2; Zhou, Xiao-Hu1,2 ; Xie, Xiao-Liang1,2 ; Liu, Shi-Qi1,2 ; Feng, Zhen-Qiu1,2 ; Hou, Zeng-Guang1,3
发表期刊	IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
ISSN	0278-0046
	2023-09-18
页码	10
通讯作者	Zhou, Xiao-Hu(xiaohu.zhou@ia.ac.cn) ; Hou, Zeng-Guang(zengguang.hou@ia.ac.cn)
摘要	The robot-assisted intervention has shown reduced radiation exposure to physicians and improved precision in clinical trials. However, existing vascular robotic systems follow master-slave control mode and entirely rely on manual commands. This article proposes a novel offline reinforcement learning algorithm, Conservative Actor-critic with SmOoth Gradient (CASOG), to learn manipulation skills on vascular robotic systems. The proposed algorithm conservatively estimates Q-function and smooths gradients of convolution layers to deal with distribution shift and overfitting issues. Furthermore, to focus on complex manipulations, transitions with larger absolute temporal-difference error are sampled with higher probability. Comparative experiments on multiple vascular models and offline data demonstrate that CASOG delivers guidewire to the target with higher success rates and fewer backward steps than prior offline reinforcement learning methods. These results indicate that the proposed algorithm is promising to improve the autonomy of vascular robotic systems.
关键词	Deep neural network offline reinforcement learning robot-assisted intervention vascular robotic system
DOI	10.1109/TIE.2023.3310021
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China
项目资助者	National Natural Science Foundation of China
WOS研究方向	Automation & Control Systems ; Engineering ; Instruments & Instrumentation
WOS类目	Automation & Control Systems ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS记录号	WOS:001122255700001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/55031
专题	多模态人工智能系统全国重点实验室
通讯作者	Zhou, Xiao-Hu; Hou, Zeng-Guang
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Macau Univ Sci & Technol, Inst Syst Engn, CASIA MUST Joint Lab Intelligence Sci & Technol, Macau, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Li, Hao,Zhou, Xiao-Hu,Xie, Xiao-Liang,et al. CASOG: Conservative Actor–Critic With SmOoth Gradient for Skill Learning in Robot-Assisted Intervention[J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS,2023:10.
APA	Li, Hao,Zhou, Xiao-Hu,Xie, Xiao-Liang,Liu, Shi-Qi,Feng, Zhen-Qiu,&Hou, Zeng-Guang.(2023).CASOG: Conservative Actor–Critic With SmOoth Gradient for Skill Learning in Robot-Assisted Intervention.IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS,10.
MLA	Li, Hao,et al."CASOG: Conservative Actor–Critic With SmOoth Gradient for Skill Learning in Robot-Assisted Intervention".IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2023):10.