基于手眼系统的视觉定位研究

Research on visual positioning based on hand-eye system

针对自动化产品装配中的视觉定位问题,搭建一套基于手眼(eye-in-hand)系统的机器视觉装配实验平台。在Halcon软件平台上运用张正友标定法对相机内参数和外参数进行标定,并利用手眼关系方程CX=XD求解出机器人的手眼关系以完成手眼系统标定的过程,最终将手眼系统标定结果应用于视觉装配平面的目标点定位。其中以机器人定位到的目标点坐标为理想位置坐标,对视觉定位与机器人定位得到的目标点位置进行比较分析,验证该手眼系统视觉定位的准确性并对视觉系统进行不确定度评定,实验重复性良好。实验结果表明,用此方法得到的手眼系统视觉定位精度能达到0.6 mm,满足机器视觉生产线上产品装配的需求。

To solve the problem of visual positioning in automated product assembly,a set of machine vision assembly experiment platform based on eye-in-hand system was built.Using the Zhang Zhengyou calibration method on the Halcon software platform to calibrate the camera parameters and external parameters,and using the hand-eye relationship equation CX=XD to solve the hand-eye relationship of the robot and to complete the calibration process of the hand-eye system,and eventually hand-eye calibration results were applied to the visual target point positioning in the plane of the assembly.The coordinates of the target points where the robot was located were the ideal position coordinates,and the position of the target points obtained by the visual positioning and robot positioning were compared and analyzed to verify the accuracy of the visual positioning of the hand-eye system,and the visual system was evaluated with uncertainty,and the experiment was repeatable.The experimental results show that the visual positioning accuracy of the hand-eye system obtained by this method can reach0.6mm and meet the requirements of product assembly on the machine vision line.