Distributed robust state and output feedback controller designs for rendezvous of networked autonomous surface vehicles using neural networks

This paper addresses the leaderless and leader–follower rendezvous problems of multiple autonomous surface vehicles subject to dynamical uncertainties and ocean disturbances. Distributed robust rendezvous controllers, based on the information of neighboring vehicles, are proposed by employing neural networks, backstepping and graph theory. Lyapunov stability analysis demonstrates that all signals in the closed-loop network are uniformly ultimately bounded. Furthermore, this result is extended to the output feedback case where only the position information can be measured. Neural network-based adaptive observers are developed to estimate the unmeasured velocity of each vehicle, and distributed observer-based rendezvous controllers are proposed. It is proved that, for both cases, rendezvous among vehicles can be reached over any connected undirected communication graphs without requiring the accurate model of each vehicle. An example is given to validate the efficacy of the proposed methods.