一种机器人视觉系统自动标定方法研究
|
摘要
本文介绍了机器人视觉系统标定的现状,以及现行标定方法的优缺点。在相机固定、机器人末端执行器在平面内运动的场合,本文利用机器人系统的通讯功能,触发相机对同一目标位置在拍照平面内多次移动机器人末端执行器的位置进行拍照,然后通过机器人程序记录多组图像点、机器人坐标点,并引入最小二乘法进行标定图像点、机器人坐标点关系,并编写相关机器人程序自动计算标定的关系因子,并进行了可靠性验证,证明了改进法计算出的工件坐标误差比常规两点方法计算出的工件坐标误差大大减小,提高了标定的速度、便捷程度、标定精度。
This paper introduces current state of calibration of robot vision system and the advantages and disadvantages of current calibration methods. When the camera is mounted on the robot end effector, the target object is photographed multiple times and the image position is obtained in the photographing plane, and the relationship between the image coordinates and the robot base coordinate system is established by the least square method. By this method,the robot program automatically calculates the relationship factor of the calibration, the reliability verification is carried out, which proves that the workpiece coordinate error calculated by the improved method is greatly reduced compared with the workpiece coordinate error calculated by the conventional two-point method. This method greatly improves the speed and convenience of calibration.
This paper introduces current state of calibration of robot vision system and the advantages and disadvantages of current calibration methods. When the camera is mounted on the robot end effector, the target object is photographed multiple times and the image position is obtained in the photographing plane, and the relationship between the image coordinates and the robot base coordinate system is established by the least square method. By this method,the robot program automatically calculates the relationship factor of the calibration, the reliability verification is carried out, which proves that the workpiece coordinate error calculated by the improved method is greatly reduced compared with the workpiece coordinate error calculated by the conventional two-point method. This method greatly improves the speed and convenience of calibration.
引文
[1]李金钟.基于单目视觉的目标点识别与导引技术研究[D].天津:天津工业大学,2018.
[2]TSAI R Y.A versatile camera calibration technique for highaccuracy 3D machine vision metrology using off-the-shelf TVcameras and lenses[J].IEEE Robotics and Automation Society,1987,3(4):323-344.
[3]段坚,张少鹏,王现康.工业机器人视觉系统的摄像机标定[J].机械工程与自动化,2013(01):97-98+101.
[4]王晓华,董煜文,李珣,等.一种提高机器人视觉系统参数标定精度的方法[J].机床与液压,2018,46(15):1-6.
[5]王炜.基于视觉引导的机器人系统标定及跟随控制的问题研究[D].武汉:湖北工业大学,2017.
[6]徐德,谭民,李原.机器人视觉测量与控制[M].北京:国防工业出版社,2011.5.
[2]TSAI R Y.A versatile camera calibration technique for highaccuracy 3D machine vision metrology using off-the-shelf TVcameras and lenses[J].IEEE Robotics and Automation Society,1987,3(4):323-344.
[3]段坚,张少鹏,王现康.工业机器人视觉系统的摄像机标定[J].机械工程与自动化,2013(01):97-98+101.
[4]王晓华,董煜文,李珣,等.一种提高机器人视觉系统参数标定精度的方法[J].机床与液压,2018,46(15):1-6.
[5]王炜.基于视觉引导的机器人系统标定及跟随控制的问题研究[D].武汉:湖北工业大学,2017.
[6]徐德,谭民,李原.机器人视觉测量与控制[M].北京:国防工业出版社,2011.5.