Dynamic Control of Three-Link SCARA Manipulator using Adaptive Neuro Fuzzy Inference System

Abstract

In this work the adaptive neuro-fuzzy inference system (ANFIS) controller is designed for the dynamic control (continuous path control) of the three-link selective compliant assembly robot arm (SCARA) manipulator. This ANFIS controller is designed to overcome the unmodeled dynamics and in the presence of structured and unstructured uncertainties of SCARA. The proposed controller-building technique combines artificial neural networks with fuzzy logic. The ANFIS control combines the advantages of neural networks (learning and adaptability) with the advantages of fuzzy logic (use of expert knowledge) to achieve the goal of robust control of robot dynamic systems. The fuzzy sets are used to formalize the level of human perception of the physical system. The neural network on the other hand performs all the necessary computations and regarding their learning capabilities, they enable an adaptation of the existing controller through its learning to the changes in the system behavior. The experimental ANFIS simulation results show very good SCARA tracking performance.