Gaussian Process Based Tracking Control for Robot Manipulators with Dynamical Uncertainties

Abstract

In this paper, we present a novel approach for tracking control of robot manipulators with dynamical uncertainties. Based on the Gaussian Process (GP), the unknown robotic dynamics are precisely modeled and estimated. And the robust tracking controller is designed in the existence of approximation error and external perturbations. The stability of the closed-loop system is proved with the Lyapunov theory. Furthermore, the effectiveness of the proposed controller is verified through simulations on a 2-DOF robot manipulator and experiments on a 6-DOF Kinova robotic arm.