Adaptive Neural Output Consensus Control of Stochastic Nonlinear Strict-Feedback Multi-Agent Systems *

An adaptive neural output consensus control issue is considered for stochastic nonlinear strict-feedback multi-agent systems (MASs). The traditional backstepping framework is employed combing with the graph theory, as well as neural networks (NNs) technology. NNs are utilized for the approximation of unknown functions, and the Itô’s lemma is used to deal with stochastic dynamics of the system. It is proved that all signals remain bounded in probability and that the tracking errors of all followers converge to a small neighborhood of the origin in the sense of mean quartic value by suitable choice of parameters. A simulation example is provided.