Neural Network Sliding Mode Control Based on Passivity Theory for Robot

The controller is designed for the problem of rigid robot tracking, which combines the skew symmetric features of robot and based on passivity theory. The sliding surface and its derivative are regarded as the input of RBF neural network, and regulate gain of sliding mode compensation controller. Thus it is good to eliminate the chattering of sliding mode control The simulation results indicate that the algorithm can not only achieve rapid tracking, improve the robustness of the system to ensure the global stability, but also effectively eliminate the chattering, in the presence of model errors and external disturbances circumstances.