A Predictor-based Neural Modified DSC Approach to Distributed Formation Tracking of Networked Marine Surface Vehicles

This paper considers the distributed formation tracking of networked marine surface vehicles with model uncertainty and time-varying ocean disturbances induced by wind, waves and ocean currents. The objective is to achieve a collective tracking with a time-varying trajectory, which can only be accessed by a fraction of follower vehicles. Distributed adaptive formation controllers are developed based on a predictor, neural networks, a tracking differentiator, and a dynamic surface control design technique. Instead of the first-order filter commonly used in traditional dynamic surface control design approach, a second-order tracking differentiator is employed to produce a fast and precise estimate of the virtual control signal prescribed by the kinematic control law. The prediction errors, rather than tracking errors, are used to update the neural adaptive laws, which enable fast identifying the vehicle dynamics without incurring high-frequency oscillations in control signals. The stability properties of the closed-loop network are established via Lyapunov analysis. Simulation results are provided to demonstrate the performance improvement of the proposed method.