Adaptive sliding mode control for robots based on fuzzy support vector machines

Abstract

To improve the control precision of robots, the control method of adaptive sliding mode for robots was presented based on fuzzy support vector machines. The sliding mode control has complete adaptability to system disturbance and siring in sliding mode, which was used to automatically track the uncertainty of system parameters and external disturbance. Fuzzy support vector machines have strong treatment of nonlinear signal and generalization ability, which was used to reduce the chattering in sliding mode control. The FSVM controller parameters were optimized by hybrid learning algorithm, which combines least square algorithm with improved genetic algorithm, to get the optimal control performance with the controlled object. The simulation results of a two-link robotic manipulator demonstrated that the control method designed gets tracking effect with high precision and speed, as well as reduces chattering of control under the condition of existing model error and external disturbance.