典型文献
Distributed Cooperative Learning for Discrete-Time Strict-Feedback Multi Agent Systems Over Directed Graphs
文献摘要：
This paper focuses on the distributed cooperative learning(DCL)problem for a class of discrete-time strict-feed-back multi-agent systems under directed graphs.Compared with the previous DCL works based on undirected graphs,two main challenges lie in that the Laplacian matrix of directed graphs is nonsymmetric,and the derived weight error systems exist n-step delays.Two novel lemmas are developed in this paper to show the exponential convergence for two kinds of linear time-varying(LTV)systems with different phenomena including the nonsym-metric Laplacian matrix and time delays.Subsequently,an adap-tive neural network(NN)control scheme is proposed by estab-lishing a directed communication graph along with n-step delays weight updating law.Then,by using two novel lemmas on the extended exponential convergence of LTV systems,estimated NN weights of all agents are verified to exponentially converge to small neighbourhoods of their common optimal values if directed communication graphs are strongly connected and balanced.The stored NN weights are reused to structure learning controllers for the improved control performance of similar control tasks by the"mod"function and proper time series.A simulation comparison is shown to demonstrate the validity of the proposed DCL method.
文献关键词：
中图分类号：
作者姓名：
Min Wang;Haotian Shi;Cong Wang
作者机构：
School of Automation Science and Engineering,South China University of Technology,Guangzhou 510641,and also with Peng Cheng Laboratory,Shenzhen 518055,China;School of Control Science and Engineering,and also with the Center for Intelligent Medical Engineering,Shandong University,Jinan 250061,China
文献出处：
引用格式：
[1]Min Wang;Haotian Shi;Cong Wang-.Distributed Cooperative Learning for Discrete-Time Strict-Feedback Multi Agent Systems Over Directed Graphs)[J].自动化学报（英文版）,2022(10):1831-1844
A类：
nonsym,neighbourhoods
B类：
Distributed,Cooperative,Learning,Discrete,Time,Strict,Feedback,Multi,Agent,Systems,Over,Directed,Graphs,This,paper,focuses,distributed,cooperative,learning,DCL,problem,class,discrete,strict,feed,multi,systems,under,graphs,Compared,previous,works,undirected,main,challenges,lie,that,Laplacian,matrix,nonsymmetric,derived,error,exist,step,delays,Two,novel,lemmas,developed,this,convergence,kinds,linear,varying,LTV,different,phenomena,including,Subsequently,adap,neural,network,NN,scheme,proposed,by,estab,lishing,communication,along,updating,law,Then,using,extended,estimated,weights,agents,verified,exponentially,small,their,common,optimal,values,strongly,connected,balanced,stored,reused,structure,controllers,improved,performance,similar,tasks,mod,function,proper,series,simulation,comparison,shown,demonstrate,validity,method
AB值：
0.573787
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
