DESIGN OF NEURO-FUZZY CONTROLLER FOR ROBOT MANIPULATOR

Abstract

The aim of the thesis is to develop an efficient dynamic control such as point to point and continuous path control strategy for Robot manipulator using fuzzy logic controller (FLC) and Neuro-Fuzzy controller. Owing to the advantage of learning ability & unique characteristics, which enable them to control the Robot manipulators. Interfacing the neural and fuzzy logic with the Robot manipulator is one of the means of getting the rapid convergence of actual joint angle trajectory to the desired joint angle trajectory. In this work, we have taken the example of the PUMA560 robot (Programmable Universal Machine for Assembly) and modeled the Fuzzy controller and ANFIS Controller, we have studied also performances obtained from Fuzzy controller,ANFIS and conventional PID controller, with the help of SIMULINK, Fuzzy logic Toolbox of The MATLAB 7.01 Software. • Results are compared with the conventional PID controller.