Ship steering control based on SA-reinforcement learning algorithm

Ship course control is closely related with navigation security, maneuverability and economy. Based on simulated annealing and reinforcement learning algorithm, a hybrid intelligent controller was proposed to ship steering. With the advantages of various intelligent algorithms, the controller can overcome the influence of the wind, wave and flow, the uncertainty of the ship steering, and the limitation that accurate data are hard to get for the disturbance and the error in instrument measuring. At last, the results of the simulation show that the ship course can be properly controlled when changeable wind and wave exist.