Active Disturbance Rejection Trajectory Tracking Control of Manipulator Based on Neural Network

In the study of the tracking characteristics of industrial manipulator, it is difficult to get the accurate system model due to the nonlinearity and uncertainty of the manipulator itself, and the traditional control theory can not achieve high-precision tracking control. In order to solve the above problems, by analyzing the dynamic model of the uncertain multi joint manipulator, based on the in-depth study of active disturbance rejection control (ADRC) and repetitive control, an ADRC algorithm with good tracking accuracy and strong robustness is proposed. In order to solve the problem that parameters are difficult to adjust, neural network is introduced to adjust the parameters. The simulation results show that the method can effectively eliminate the tracking error, improve the robustness of the system, and meet the tracking accuracy of the uncertain multi joint manipulator.