Development of an intelligent system for prediction of inverse kinematics of robot manipulator

Abstract

Inverse kinematics comprises the computation need to find the joint angles for a given Cartesian position and orientation of the end effectors. There is no unique solution for the inverse kinematics thus necessitating application of artificial neural network models. This paper proposes three different types of structured artificial neural network (ANN) models to find the solution of inverse kinematics. The first one is an ANN model which is MLP (multi-layer perceptron’s) and is popular as back propagation neural network model. In this gradient descent type of learning rules are applied. The second kind of ANN model is PPN (polynomial poly-processor neural network) where polynomial equation is used and the last one is Pi-network.