Neural network based adaptive dynamic surface control for cooperative path following of marine surface vehicles via state and output feedback

This paper addresses the problem of steering a group of marine surface vehicles along given spatial paths, while holding a desired formation pattern subject to dynamical uncertainty and ocean disturbances induced by unknown wind, waves and ocean currents. The control design is categorized into two envelopes. One is to steer individual marine surface vehicle to track a given spatial path. The other is to synchronize the speed of each vehicle along its path and path variables under the constraints of an underlying communication network in order to holding a desired formation pattern. The key features of the developed controllers are that, first, the neural network adaptive technique allows one to handle the dynamical uncertainty and ocean disturbances, without the need for explicit knowledge of the model; second, the proposed dynamic surface control technique simplifies the controller design by introducing the first-order filters and avoids the calculation of derivatives of virtual control signals. Further, this result is extended to the output feedback case, where a high-gain observer based cooperative path following controller is developed without measuring the velocity of each vehicle. Under the proposed controllers, all signals in the closed-loop system are guaranteed to be uniformly ultimately bounded for both state and output feedback cases. Simulation results validate the performance and robustness improvement of the proposed strategy.