Neural Network-Based Finite-Time Trajectory Tracking Control of Uncertain Robotic Manipulators

Abstract

The problem of finite-time trajectory tracking control is studied for rigid-link robotic manipulators. The non-singular fast terminal sliding mode controller combining with RBF neural network is designed to ensure that the tracking errors converge to a small neighborhood of zero in a finite time. The radial basis function is employed to compensate the parametric uncertainty and uncertain external disturbances. The non-singular fast terminal sliding mode control scheme is adopted to improve fast convergence of tracking errors. Moreover, the stability of system is proved rigorously in the Lyapunov framework. Numerical simulation results of two-link robot manipulators illustrate the effectiveness of the proposed controller.