NN-based visual servoing compensation control of a Gough-Stewart platform with uncertain load

This paper addresses the trajectory tracking control of a Gough-Stewart platform (GS platform) with an uncertain load. The uncertainty of this load leads to external disturbance to the parallel robot, which affects the dynamic coupling among the six degrees of freedom (DOF) and the tracking performance. Even though many researchers focus on improving the system robustness and tracking accuracy, there still exist two main problems: the system's internal uncertainties, including the modeling, manufacturing, and assembly errors of the parallel robot affect the control accuracy; the uncertain external disturbance varies in an extensive range and reduces the stability and tracking accuracy of the system. Therefore, we propose a novel control methodology: the dynamic Image-based visual servoing (IBVS) Radial basis function neural network (RBFNN) real-time compensation controller. This control considers an acceleration model of visual servoing and performs real-time compensation for the enormous uncertain disturbance from the load with RBFNN. The stability of the proposed controller is fully investigated with the Lyapunov method. Simulations are performed on a GS platform with an uncertain load to test the controller's performance. It turns out that this controller provides good tracking accuracy and robustness simultaneously.