Kinematics positive solution of 6-PSS parallel robot based on BP neural network

Abstract

A method based on the neural network for the kinematics solution of 6-PSS parallel robot was proposed. The training samples were obtained through the inverse kinematics. In this paper,the neural network was trained by Levenberg-Marquardt method to realize nonlinear mapping between the joints space and the Cartesian space, also, it provided the kinematics positive value. Compared with the numerical analysis method,the result shows this method gets a high precise value and spends a little time, so it can be applied in the real time control on task space or in getting the work space of the mechanism.