Direct adaptive NN control of ship course autopilot with input saturation

In this paper, a novel direct adaptive NN control algorithm is proposed for a class of ship course autopilot with input saturation. Neural networks (NNs) are used to tackle unknown nonlinear function, and then an adaptive NN controller is constructed by combining Lyapunov function and the backstepping technique. By utilizing a special property of the affine term, the developed scheme avoids the controller singularity problem completely, and the stability analysis subject to the effect of input saturation constrains is conducted by employing an auxiliary design system. It is also proved that the proposed algorithm could guarantee the closed-loop system to be uniformly ultimately bounded and the output of the system is proven to converge to a small neighborhood of the desired trajectory. Finally, simulation studies are given to illustrate the effectiveness and the performance of the proposed scheme.