Industrial robot hand-eye calibration method based on calibration ball

Abstract

The invention discloses an industrial robot hand-eye calibration method based on a calibration ball, and the method comprises the following steps: fixing a 3D area-array camera at the tail end of a robot, fixing the calibration ball on the ground, and measuring the actual coordinates of the calibration ball; adjusting different poses of the robot in each working area, recording different pose dataof the robot, and acquiring 3D point cloud data of the calibration ball of the robot under the corresponding pose through the 3D area-array camera to obtain a pose-calibration ball 3D point cloud data set; processing the 3D point cloud data of the calibration ball under the corresponding pose, fitting the 3D point cloud data of the calibration ball under the corresponding pose, and calculating aball center coordinate; and calibrating the robot through the different pose data and sphere center measurement coordinates under the corresponding pose as well as the actual coordinates of the calibration ball. The method facilitates calibration of the robot, is simple and easy to implement, and is quick and accurate.

Description

technical field [0001] The invention relates to the technical field of 3D vision, in particular to a hand-eye calibration method for an industrial robot based on a calibration ball. Background technique [0002] The robot's motion coordinate system and the camera's coordinate system are combined through "hand-eye calibration". Here, the end effector of the robot can be regarded as a human hand, and the visual sensor can be regarded as a human eye. Robot hand-eye systems are generally divided into two types, eye-in-hand and eye-to-hand. The former fixes the visual sensor on the end effector of the robot, which can follow the end of the robot. Motion, which fixes the vision sensor in the environment and does not move with the end of the robot. The former tend to have higher dexterity and allow for greater precision in the robot's movements. [0003] In the process of parts inspection, we usually need to calibrate the robotic arm and 3D camera of the robot first. The traditio...

AI Technical Summary

Problems solved by technology

[0003] In the process of parts inspection, we usually need to calibrate the robotic arm and 3D camera of the robot first. The traditional hand-eye calibration method is cumbersome, requires multiple sampling, and manual operation, which is time-consuming and labor-intensive, and the accuracy is not high.

Images