Rendezvous of networked autonomous surface vehicles with distributed neural protocols

This paper is concerned with the rendezvous problem of multiple autonomous surface vehicles subject to environmental disturbances and dynamical uncertainties. Distributed neural rendezvous protocols, based on the positions of neighboring vehicles, are proposed by employing neural networks, back-stepping and graph theory. The control design is developed for connected undirected communication graphs without requiring the accurate models of the vehicles. Based on Lyapunov analysis, all signals in the closed-loop networked system are guaranteed to be uniformly ultimately bounded. Simulation results demonstrate the efficacy of the proposed method.