Learning from adaptive neural network output feedback control of uncertain ocean surface ship dynamics

This paper studies the problem of learning from adaptive neural network (NN) output feedback control of ocean surface ship without velocity measurements in uncertain dynamical environments. When only ship position and heading measurements are available for identification and control, using a high-gain observer to estimate the unmeasurable velocities, we propose stable adaptive output feedback NN tracking control. Partial persistent excitation condition of some internal signals in the closed-loop system is satisfied during tracking control to a recurrent reference trajectory. Under the persistent excitation condition, the proposed adaptive NN control is shown to be capable of acquiring knowledge on the uncertain ship dynamics in the stable control process and of storing the learned knowledge in memory. Subsequently, a novel NN learning control method exploiting the learned knowledge without readapting to the unknown ship dynamics is proposed to achieve closed-loop stability and the improvement of the control performance. Simulation studies are performed to demonstrate the effectiveness of the proposed method. Copyright (c) 2012 John Wiley & Sons, Ltd.