ROBUST ADAPTIVE TRAJECTORY TRACKING CONTROL FOR ROBOT MANIPULATORS WITH DEAD-ZONES AND EXTERNAL DISTURBANCES USING SLIDING MODE CONTROL AND RBF NEURAL NETWORKS

Abstract

The tracking performance of robot manipulators is often compromised by dynamic uncertainties, external disturbances, and actuator nonlinearities such as dead zones. To overcome these issues, this study introduces a robust adaptive control framework that combines sliding mode control (SMC) with three radial basis function (RBF) neural networks. Within this framework, the first RBF network approximates unmodeled dynamics and disturbances, the second captures the dead-zone characteristics, and the third compensates for the associated nonlinear effects. The SMC component enhances robustness against approximation errors and disturbances, while adaptive update laws, designed via Lyapunov analysis, ensure that the tracking error converges to a bounded neighborhood of the origin. Simulation results on a robot manipulator validate that the proposed approach achieves high tracking accuracy and preserves system stability under severe disturbances and significant dead-zone effects