基于神经网络的鲁棒自适应滑模迭代学习控制

对一类不确定非线性系统，包括不确定性机器人，提出一种自适应鲁棒迭代学习控制方案，学习控制用于学习周期性的系统不确定性，自适应滑模控制用于抑制非周期性系统不确定性，并且利用RBF神经网络自适应学习系统不确定性的未知上界，对不确定性系统动态和有界输入拢动具有鲁棒性，通过Lyapunov直接方法，确保了对每次迭代闭环系统是一致有界的，并且沿着迭代次数的增加，跟踪误差渐近收敛于零，仿真结果表明了该方案的有效性。

Robust adaptive sliding mode iterative learning control based on the neural network

An adaptive robust iterative learning control scheme is developed for a class of uncertain nonlinear systems, including robotics as a subset. The learning control part is utilized to learn the periodic uncertainties and the robust part is to suppress the non-periodic system uncertainties. An RBF neural network is used to adaptively learn the unknown bounds of system uncertainties. The proposed scheme achieves robustness to uncertain dynamics and bounded input disturbances. By Lyapnov's direct method, the overall closed-loop stability and the asymptotic convergence of the tracking error to zero in the iteration domain are established. The validity of the proposed scheme is confirmed with a simulation example.