A general fuzzified CMAC based reinforcement learning control for ship steering using recursive least-squares algorithm

A general fuzzified cerebellar model articulation controller (GFCMAC) is proposed. The mapping of receptive field functions, the selection law of membership function and the learning algorithm are presented. Recursive least-squares temporal difference algorithm (RLS-TD) is deduced, which can use data efficiently with faster convergence and less computational burden. Using RLS-TD method a reinforcement learning structure based on GFCMAC is applied to ship steering control, as provides an efficient way for the improvement of ship steering control performance. The parameters of controller are online learned and adjusted. Simulation results show that the ship course can be properly controlled in case of the disturbances of wave and wind. It is demonstrated that the proposed algorithm is a promising alternative to conventional autopilots.