Online RBF and fuzzy based sliding mode control of robot manipulator

Abstract

The aim of this work is the combination of radial basis function networks (RBF) and fuzzy techniques to enhance the sliding mode controllers. In fact, three RBFs networks were used to estimate the model parameters and to respond to model variation and disturbances, a sequential training algorithm based on Kalman filter was implemented, and to eliminate the chattering effect, a fuzzy controller was designed. The hybrid sliding mode controller had shown a strong ability to get over noise and uncertainties. The former controller was used to control a two degree of freedom robot manipulator.