Adaptive steering control system of the USV with friction compensation

Friction exists widely in the relative movement of mechanical devices. Considering the rotation friction in the autopilot of Unmanned Surface Vehicle (USV), an adaptive steering control system with friction compensator is designed in this paper. Taking the nonlinearity and parameters uncertainties of USV into account, the sliding mode control technology combined with a friction compensator is utilized to realize the steering control. The Radial Basis Function (RBF) neural network is integrated to approximate the friction disturbance online. The weights of the neural network are updated according to the adaptive law, which is derived by using the Lyapunov method. To solve the system chattering problem existing in the control, the sign function which is in the switch control is substituted by a saturation function. The controller proposed in this paper works well in the presence of friction disturbance which is verified by the simulation results. Compared with the traditional sliding mode controller, it has higher tracking accuracy.