Intelligent Computation of Inverse Kinematics of a 5-dof Manipulator Using MLPNN

Abstract

This paper presents inverse kinematic solution of 5 degree of freedom robot manipulator. Inverse kinematics is computation of all joint angles and link geometries which could be used to reach the given position and orientation of the end effector. This computation is very difficult to attain exact solution for the position and orientation of end effector due to the nature of non- algebraic equation of inverse kinematics. Therefor it is required to use some soft computing technique for the solution of inverse kinematics of robot manipulator. This paper presents structured artificial neural network (ANN) model from soft computing domain. The ANN model used is a Multi Layered Perceptron Neural Network (MLPNN). In this gradient descent type of learning rules are applied. An attempt has been made to find the best ANN configuration for the problem. It was found that between multi-layered perceptron neural network giving better result and calculated mean square error, as the performance index.