La Synthèse d’une Commande intelligente des systèmes Robotiques

Abstract

In this thesis, we are interested in the field of intelligent control of nonlinear robotic systems, and more particularly that of the PUMA 560 manipulator robot. The main objective is to design a robust and efficient control by combining three advanced approaches: sliding control, fuzzy logic and neural networks. The proposed hybrid control makes it possible to take advantage of the advantages of each method while mitigating their disadvantages. We used the MATLAB/Simulink environment to validate the effectiveness of the proposed technique. The simulation results demonstrate a significant improvement in performance in terms of trajectory tracking, robustness and chattering reduction, compared to conventional approaches. On the other hand, to implement nonlinear controls in real time, we presented an implementation of a nonlinear scheme of genetic algorithms on a DC motor using MATLAB and Arduino.