欠驱动水面无人艇鲁棒自适应位置跟踪控制

An neural network adaptive position tracking control strategy for underactuated unmanned surface vehicle (USV) is proposed to solve the problem of horizontal position tracking of underactuated USV with unknown uncertainties. A nonlinear controller is designed by using the backstepping method. The dynamic surface method is used to obtain the derivative of dummy variable, which reduces the complexity of direct derivation of dummy variables. The uncertain function of USV system is approximated by employing the neural network adaptive method, which overcomes parameter uncertainty problem. An exponentially convergent current observer is designed to effectively estimate the constant current velocity. The stability of the closed-loop control system is proved by using Lyapunov stability theory. Finally, the effectiveness and robustness of control strategy are verified by simulation experiments.