机器人的神经网络鲁棒轨迹跟踪控制

考虑了一类具有外界扰动和参数不确定性机器人系统的轨迹跟踪鲁棒控制问题。提出了两种控制方法：第一种应用输入输出线性化方法以及Lyapunov函数法，推导出鲁棒输出跟踪控制器。所获得的控制器可确保系统输出按指数规律跟踪期望输出，同时相应闭环系统的状态一致最终有界。第二种方法在第一种控制方法的基础上，利用一个RBF神经网络自适应学习系统不确定性的未知上界，有效的克服了系统不确定性的影响，提高了控制精度。

Neural network robust control for trajectory tracking of robot manipulators

The neural robust control for trajectory tracking of a class of robot manipulators with diaturbance and parameter uncertainties is considered. The robust output-tracking controller is constructed by employing input/output feedback linearization approach and Lyapunov method, and the obtained controller guarantees that the system output can track the desired output with exponential law and all states of the obtained closed-loop system are uniformly ultimately bounded. Furthermore, a RBF neural network is used to learn the unknown upper bound of system uncertainties, which effectively eliminate the effects of system uncertainties and improve the control accuracy.