A fast and straightforward hand-eye calibration method using stereo camera

Abstract

Robot hand-eye calibration is crucial for a robot to transform the target 3D position from the camera coordinate system into the robot coordinate system. The conventional method is to use a single-lens camera and calibration board and then solve the AX=XB problem. Recently with the popularization of stereo camera in robot industry, we design a fast and straightforward way to accomplish hand-eye calibration using the point cloud information from the stereo camera and orthogonal projection. We also investigate the number of pairs of data required for calculation in this procedure. We conclude that normally a minimal of 6 points are required for obtaining satisfying result and more pairs of data can provide better result. The procedure is demonstrated and tested on an electric robot arm, and further validated on a full ocean depth hydraulic robot arm. The procedure takes little time to set up and the formulas are concise. It can be applied easily to most robot arms for hand-eye calibration.