A Comparative Study of Prediction of Inverse Kinematics Solution of 2-DOF, 3-DOF and 5-DOF Redundant Manipulators by ANFIS

Abstract

In this paper, a method for solving forward and inverse kinematics of redundant manipulator is proposed. Obtaining the joint variables of these manipulators from a desired position of the robot end-effector called as inverse kinematics (IK), is one of the most important problems in robot kinematics and control. The difficulties in solving the IK equations of these redundant robot manipulator arises due to the presence of uncertain, time varying and non-linear equations having transcendental functions. The ability of ANFIS (Adaptive Neuro-Fuzzy Inference System) is used in this paper, to predict the IKs solution of this manipulator. A single-output Sugeno- type FIS (Fuzzy Inference System) using grid partitioning has been modelled in this work. The Denavit-Harbenterg (D-H) notation is used to model robot links and solve the transformation matrices of each joint. The forward kinematics and inverse kinematics for a 2-DOF, 3-DOF and 5-DOF robot manipulator are analysed symmetrically to shows the effectiveness of this approach. The Efficiency of ANFIS can be concluded by observing the surface plot, residual plot and normal probability plot of generated data.