Data-Based Approximate Policy Iteration for Optimal Course-Keeping Control of Marine Surface Vessels.

In this paper, the data-based approximate policy iteration (API) method is used for optimal course-keeping control with unknown ship model. When we deal with the nonlinear optimal control problem, the Hamilton Jacobi Bellman (HJB) equation, which is difficult to be solved analytically, needs to be tackled. Furthermore, because of numerous parameters to be determined and unknown nonlinear terms, it is usually difficult to establish the accurate mathematical model for ships. In order to overcome these difficulties, the API method, which can solve the problem of model-free system, is introduced for optimal course-keeping control of marine surface vessels. And the asymptotic stability of the closed-loop system can be guaranteed via Lyapunov analysis. Finally, a numerical example is provided to demonstrate the effectiveness of the control scheme.