Data Driven Iterative Learning Control Method for Rehabilitation Training Robot System

In the practical application of the rehabilitation training robot system, rehabilitation robots usually need to perform highly repetitive tasks, and the input and expected output of each task are relatively fixed. In order to address the impact of changes in model parameters on the tracking performance of the human-machine system and improve the safety of the motion trajectory of the rehabilitation training robot, this paper proposes a data-driven iterative learning control method. By designing a recursive data estimation algorithm for the pseudo-Jacobi matrix, a data model of the human-machine system is established. On this basis, a data-driven iterative learning controller is designed, and the stability of the tracking error system is analyzed. The simulation and experimental results show that the control method proposed in this paper enhances the robustness of the tracking motion of the human-machine system and the safety of the motion trajectory.