Neural network control of a parallel robot

Abstract

This paper presents a method for obtaining the inverse kinematics of a six degree of freedom error compensation device for a robotic manipulator. The error compensation device is based on a parallel link structure having two circular platforms connected by six links, each with double spherical joints. A three layer backpropagation neural network algorithm was applied to compute the kinematics and control the mechanism. Simulation results based on the proposed technique are described.