Online approximate solution of HJI equation for unknown constrained-input nonlinear continuous-time systems

doi:10.1016/j.ins.2015.09.001

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

	Online approximate solution of HJI equation for unknown constrained-input nonlinear continuous-time systems
	Yang, Xiong; Liu, Derong; Ma, Hongwen; Xu, Yancai
发表期刊	INFORMATION SCIENCES
	2016-01-20
卷号	328 页码:435-454
文章类型	Article
摘要	This paper is concerned with the approximate solution of Hamilton-Jacobi-Isaacs (HJI) equation for constrained-input nonlinear continuous-time systems with unknown dynamics. We develop a novel online adaptive dynamic programming-based algorithm to learn the solution of the HJI equation. The present algorithm is implemented via an identifier-critic architecture, which consists of two neural networks (NNs): an identifier NN is applied to estimate the unknown system dynamics and a critic NN is constructed to obtain the approximate solution of the HJI equation. An advantage of the proposed architecture is that the identifier NN and the critic NN are tuned simultaneously. With introducing two additional terms, namely, the stabilizing term and the robustifying term to update the critic NN, the initial stabilizing control is no longer required. Meanwhile, the developed critic tuning rule not only ensures convergence of the critic to the optimal saddle point but also guarantees stability of the closed-loop system. Moreover, the uniform ultimate boundedness of the weights of the identifier NN and the critic NN are proved by using Lyapunov's direct method. Finally, to illustrate the effectiveness and applicability of the developed approach, two simulation examples are provided. (C) 2015 Elsevier Inc. All rights reserved.
关键词	Adaptive Dynamic Programming Hamilton-jacobi-isaacs Equation Input Constraint Neural Network Optimal Control Reinforcement Learning
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.ins.2015.09.001
关键词[WOS]	ZERO-SUM GAMES ; DYNAMIC-PROGRAMMING ALGORITHM ; ADAPTIVE OPTIMAL-CONTROL ; STATE-FEEDBACK CONTROL ; H-INFINITY CONTROL ; LEARNING ALGORITHM ; NEURAL-NETWORKS ; CONTROL DESIGN ; ARCHITECTURE ; FORMULATION
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61034002 ; Beijing Natural Science Foundation(4132078) ; Early Career Development Award of the State Key Laboratory of Management and Control for Complex Systems (SKLMCCS) ; 61233001 ; 61273140 ; 61304086 ; 61374105)
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems
WOS记录号	WOS:000365054800028
引用统计	被引频次：60[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/173211/10518
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
作者单位	Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Yang, Xiong,Liu, Derong,Ma, Hongwen,et al. Online approximate solution of HJI equation for unknown constrained-input nonlinear continuous-time systems[J]. INFORMATION SCIENCES,2016,328:435-454.
APA	Yang, Xiong,Liu, Derong,Ma, Hongwen,&Xu, Yancai.(2016).Online approximate solution of HJI equation for unknown constrained-input nonlinear continuous-time systems.INFORMATION SCIENCES,328,435-454.
MLA	Yang, Xiong,et al."Online approximate solution of HJI equation for unknown constrained-input nonlinear continuous-time systems".INFORMATION SCIENCES 328(2016):435-454.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Online approximate s（833KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载