NEURO-FUZZY CONTROLLER FOR A THREE-LINK ROBOTIC MANIPULATOR

Abstract

The very precise control of robot manipulator to track the desired trajectory is a very tedious job and almost unachievable with the help of conventional controllers. This task is achievable to certain limit with the help of adaptive controller but these also have their own limitations of assuming that the system parameters being controlled change relatively slowly. Many algorithms have been proposed from time to time to minimize these deficiencies. Interfacing the neural network and fuzzy logic with the robot manipulator is one of the means of getting the rapid convergence of actual trajectory to the desire trajectory. In this work, we have taken the example of the three-link manipulator and modeled the ANN controller. We have studied also performances obtained from the neural network controller with the help of simulation program. In addition an approach for further improving the performance by using fuzzy logic has been described for possible future extension