Abstract
Abstract
Precise trajectory tracking is a difficult task due to partially known and unknown dynamics and the disturbances present in the system. For improving the tracking performance of the robotic manipulator, this work proposes a novel PSO optimized kernel based Extreme Learning Machine (PSO-KELM) learning algorithm in which PSO is used to get the optimal values of the free kernel-parameters in KELM. The simulation results represent the good generalized performance and PSO-KELM outperforms the KELM and ELM based control techniques for the manipulator trajectory tracking. Comparative analysis of the proposed control schemes have been done with NN and SVM based controllers and various ELM based variants for the trajectory tracking problem in robotic manipulator.