Path following of marine surface vehicles with dynamical uncertainty and time-varying ocean disturbances

This paper addresses three interrelated problems concerning the path following of marine surface vehicles, namely, the path planning, the guidance, and the velocity controller design. A modified cubic spline interpolation technique is employed to design a path that is connected by a series of way-points. The line-of-sight (LOS) algorithm is applied in guidance system design, where the drift force due to the vehicle sideslip is compensated by an integral term. The velocity controller is designed by combining the dynamic surface control (DSC) design and a novel predictor based iterative neural network (PINN) control method. Specifically, neural network (NN) with iterative updating laws based on prediction errors are proposed to identify the dynamical uncertainty and time-varying ocean disturbances. Using a Lyapunov–Krasovskii functional, it is proven that all error signals in the system are uniformly ultimately bounded. Comparison studies are given to show the effectiveness of the proposed method.