考虑输入饱和的无人艇神经网络命令滤波反步控制

Neural Network-Based Command Filtered Backstepping Control for USV with Input Saturation

针对具有输入饱和和未知非线性的无人水面艇(USV)系统的轨迹跟踪控制问题,提出一种基于命令滤波反步的自适应轨迹跟踪控制策略。利用径向基函数神经网络(RBFNN)逼近系统中的未知动态,减少了需要设计的自适应律数量,降低了系统的复杂度,并基于反步法设计了系统的控制律;通过引入命令滤波器及其补偿机制,解决了计算复杂的问题,消除了滤波误差的影响,提高了系统的控制精度;最后仿真验证了所提方法的有效性。

A command filtered backstepping control method is proposed for the trajectory tracking problem of unmanned surface vehicle(USV)system with input saturation and unknown nonlinearity.The radial basis function neural network(RBFNN)is used for the approximation of the unknown dynamics,which can reduce the amount of adaptive laws and the complexity of the system.The control law is designed by the backstepping method.The command filter with error compensation mechanism is introduced into the system and the effect of filtering error is eliminated so that the control accuracy is improved.Finally,the effectiveness of the method is shown by the simulation experiment.