Position Control of a Single Link Flexible Joint Robot Manipulator using Adaptive Neuro-Fuzzy Control System

Abstract

The advance methodologies to optimize fuzzy logic controller parameters via neural network and use the neuro- fuzzy scheme to control the single link flexible joined robot manipulators. The dynamics of robot single link manipulators are highly nonlinear with strong couplings existing between joints and are frequently subjected to structured and unstructured uncertainties. The increased complication of robots manipulator considering joint elasticity makes conventional model-based control strategies complex and difficult to manufacture. This paper presents investigations into the development of neuro fuzzy control for position control of a single link flexible joint manipulator. To study the effectiveness of the controllers, an adaptive Neuro Fuzzy Controller is developed for tip angular position control of a flexible joint manipulator. This is then extended to incorporate a neuro fuzzy Controller for position error decrease of the flexible joint system. Simulation results of the response of the flexible joint manipulator with the controllers are obtained in time domains. The performances of the adaptive neuro fuzzy control schemes are examined in terms of input tracking of position in robotics, and also graphically plotted in time response specifications.