An off-policy iteration algorithm for robust stabilization of constrained-input uncertain nonlinear systems

doi:10.1002/rnc.4342

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 复杂系统智能机理与平行控制团队

	An off-policy iteration algorithm for robust stabilization of constrained-input uncertain nonlinear systems
	Yang, Xiong1 ; Wei, Qinglai2
发表期刊	INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
ISSN	1049-8923
	2018-12-01
卷号	28 期号:18 页码:5747-5765
通讯作者	Yang, Xiong(xiong.yang@tju.edu.cn)
摘要	This paper studies the robust stabilization problem of constrained-input nonlinear systems with mismatched uncertainties. Initially, the robust stabilization problem is converted into a constrained H-2 optimal control problem by providing a proper infinite-horizon cost function for the auxiliary system. It is demonstrated that the solution of the constrained H-2 optimal control problem can force the original system to be stable in the sense of uniform ultimate boundedness. Then, under the framework of reinforcement learning, an off-policy iteration algorithm is proposed to solve the constrained H-2 optimal control problem. The off-policy iteration algorithm is implemented by using two kinds of approximators. That is, the critic approximator is applied to approximate the optimal cost function and the actor approximator is used to approximate the augmented optimal control. The method of weighted residuals together with the Monte-Carlo integration technique is employed to determine the weight parameters of critic and actor approximators. Finally, two examples, including a pendulum system, are presented to validate the proposed control algorithm.
关键词	constrained input mismatched uncertainties off-policy iteration reinforcement learning robust stabilization
DOI	10.1002/rnc.4342
关键词[WOS]	H-INFINITY CONTROL ; CONTINUOUS-TIME SYSTEMS ; TRACKING CONTROL ; REINFORCEMENT ; DESIGN
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61503379] ; National Natural Science Foundation of China[61722312] ; China Scholarship Council under the State Scholarship Fund ; National Natural Science Foundation of China[61503379] ; National Natural Science Foundation of China[61722312] ; China Scholarship Council under the State Scholarship Fund
项目资助者	National Natural Science Foundation of China ; China Scholarship Council under the State Scholarship Fund
WOS研究方向	Automation & Control Systems ; Engineering ; Mathematics
WOS类目	Automation & Control Systems ; Engineering, Electrical & Electronic ; Mathematics, Applied
WOS记录号	WOS:000450110800005
出版者	WILEY
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/22564
专题	多模态人工智能系统全国重点实验室_复杂系统智能机理与平行控制团队
通讯作者	Yang, Xiong
作者单位	1.Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300072, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Yang, Xiong,Wei, Qinglai. An off-policy iteration algorithm for robust stabilization of constrained-input uncertain nonlinear systems[J]. INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL,2018,28(18):5747-5765.
APA	Yang, Xiong,&Wei, Qinglai.(2018).An off-policy iteration algorithm for robust stabilization of constrained-input uncertain nonlinear systems.INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL,28(18),5747-5765.
MLA	Yang, Xiong,et al."An off-policy iteration algorithm for robust stabilization of constrained-input uncertain nonlinear systems".INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL 28.18(2018):5747-5765.