Cooperative Learning for Switching Networks With Nonidentical Nonlinear Agents

• 成果类型: Article
• 署名作者: Meng, Deyuan; Zhang, Jingyao
• 署名单位: Beihang University; Beihang University
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2021.3059791
• 发表日期: 2021
• 页码: 6131-6138
• 关键词: Switches; uncertainty; TOPOLOGY; Task analysis; Protocols; indexes; CONVERGENCE; Cooperative learning; Distributed control; Multiagent system (MAS); nonidentical nonlinearity; switching topology

摘要

This article is aimed at realizing cooperative learning for networked multiagent systems subject to uncertain nonlinear dynamics and switching topologies. A distributed control protocol is proposed by integrating the nearest neighbor rules and iterative updating rules. Thanks to cooperative learning, all agents can be ensured to track any prescribed reference robustly over any finite interval, regardless of the nonidentical locally Lipschitz nonlinearities of agents, initial state shifts, and external disturbances. Moreover, a convergence analysis approach to cooperative learning is given by exploring the properties for the products of stochastic matrices that are associated with switching digraphs.