An online offset correction method and device for robot hand-eye calibration

Abstract

The invention relates to an online offset correction method and device for robot hand-eye calibration. The method includes: obtaining the coordinate values ​​of the centers of nine circles on the calibration board in the camera coordinate system and the base coordinate system, and establishing the coordinates of each circle on the calibration board. The transformation equation of the center of the circle from the camera coordinate system to the robot base coordinate system, through the offset coordinates of each circle, using the least squares method to calculate the homogeneous transformation matrix of the camera coordinate system relative to the robot base coordinate system; according to the calibrated camera coordinate system Relative to the pose value of the base coordinate system, the error of the calibration result is corrected for the offset of the nine circles on the calibration board using the vector two-norm formula, and its accuracy is analyzed and evaluated. The invention corrects the offset of the robot's hand-eye calibration process, can realize flexible, accurate and fast adjustment on the production line, can realize high repeatability and precise grasping operation, and can be applied to the operation of the SCARA robot's hand-eye device, which is simple and efficient High precision.

Description

technical field [0001] The invention belongs to the technical field of machine vision, and more specifically relates to an online offset correction method and device for robot hand-eye calibration. Background technique [0002] With the development of artificial intelligence technology, the application of robots is becoming more and more extensive. For example, the four-axis SCARA industrial robot is widely used in the grasping operation of the production line, and its requirements for the accuracy of the robot's hand-eye calibration are getting higher and higher. In the current robot hand-eye calibration method, in most cases, the calibration point of the image captured by the camera is in the robot workspace, but in the actual automated production line, the calibration point of the image captured by the camera is not in the robot workspace, and the calibration point needs to pass through The movement can only reach the situation in the workspace of the robot, that is, the...

AI Technical Summary

Problems solved by technology

In the current robot hand-eye calibration method, in most cases, the calibration point of the image captured by the camera is in the robot workspace, but in the actual automated production line, the calibration point of the image captured by the camera is not in the robot workspace, and the calibration point needs to pass through Movement can only reach the situation in the robot's workspace, that is, there is an offset problem in hand-eye calibration

In addition, there is a deflection problem of the base coordinate system in the actual installation process of the robot, which will also reduce the accuracy of the robot's hand-eye calibration

Images