抄録
Iterative learning learning controllers are good choice in the repetitive trajectory tracking tasks because they do not need identification of a nonlinear system which by itself is a difficult task. Starting from a zero knowledge about the system, these type of learning controllers take certain number of iterations before converging to the desired trajectory. In this paper, intelligence is incorporated in the iterative learning controllers using neural networks for a class of nonlinear systems. Our proposed method is proved to be very effective in improving the convergence of the tracking error. The proposed method is very general and applicable to most of the iterative learning controller without modifying their the simple learning structures.
