Hybrid Intelligent Ship Steering Controller Based on Backstepping Approach

Ship course control is closely related with navigation security, maneuverability and economy. In the paper, based on Backstepping algorithm, a hybrid intelligent controller is proposed to ship steering control. The controller is a nonlinear controller in nature, whose design is simpler and more intuitive than its linear counterparts. For the adaptive laws of the controller are derived in the sense of Lyapunov function, the stability can be guaranteed. With the advantages of intelligent algorithms, RBF neural network and Reinforcement Learning algorithm, which are utilized in this paper, 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. Al last, the results of the simulation show that the ship course can be properly controlled when changeable wind and wave exist and the accurate data can't be obtained.