Improvement of robot accuracy by calibrating kinematic model using a laser tracking system-compensation of non-geometric errors using neural networks and selection of optimal measuring points using genetic algorithm-

Abstract

A laser tracking system is employed for measuring robot arm's tip with high accuracy. Geometric parameters in a robot kinematic model are calibrated by minimizing errors between measured positions and predicted ones based on the model. Residual errors caused by non-geometric parameters are further reduced by using neural networks, realizing high positioning accuracy of sub-millimeter order. To speed up the calibration process, the smaller number of measuring points is preferable. Optimal measuring points, which realize high positioning accuracy with small point number, are selected using genetic algorithm (GA).