DESIGN ADAPTIVE TRAJECTORY TRACKING CONTROLLER FOR ROBOT MANIPULATORS BASED ON NEURAL NETWORK

Abstract

This paper proposes a trajectory tracking controller based on adaptive neural
networks (ANNs) for robot manipulators (RMs) to achieve the high precision
position tracking performance. In this controller, adaptive radial basis function
(RBF) neural networks control is investigated to control the joints position and
approximate the unknown dynamics of an n-link robot manipulators. The
adaptive RBF network can effectively improve the control performance against
large uncertainty of the system. The online adaptive control training laws are
determined by Lyapunov stability and the approximation theory, so that
uniformly stable adaptation is guaranteed, and asymptotically tracking is
achieved. In adition, a robust control is constructed as an auxiliary controller to
suppress the neural network modeling errors and the bounded disturbances to
guarantee the stability and robustness under various environments such as the
mass variation, the external disturbances and modeling uncertainties. Finally,
simulation examples are given to illustrate the effectiveness of the proposed
approach control system for two link-robot manipulators. From simulation
results, we can find that the proposed adaptive control has fast reduction rate in
tracking errors and tracking errors is converged to zero when t → ∞. Moreover,
when the tracking errors reach the big value, there is little chattering in torque.