A Fast Calibration of Laser Vision Robotic Welding Systems Using Automatic Path Planning

摘要

Calibration is a crucial issue in laser vision robotic welding systems (LVRWSs). Traditional calibration methods rely on complex manual teaching and fixed pattern of robot end-effector poses, which are time-consuming and will occasionally fall into local optimal solution. To address these issues, a fast calibration method based on automatic path planning is proposed in this article. By ensuring that the camera’s optical axis coincides with the center of the calibration board regardless of the robot end-effector’s attitude, images covering all feature points will be collected. Based on the camera optical axis constraint, we establish the robot end-effector motion constraint equation. Then, an automatic path planning method based on optical axis constraint equation, rotation constraint, and motion selection strategy is proposed, which improves the diversity of the calibration data. During data acquisition, a hand–eye parameters optimization process is performed simultaneously by minimizing the reprojection error of visual feature points. The actual calibration tests show that the proposed method can significantly improve the calibration efficiency and robustness. In addition, a variety of weld measurement experiments, such as S-type and C-type welds and filet weld, were conducted under arbitrary welding torch’s attitude to evaluate the accuracy and robustness of the method. The mean absolute error (MAE) and root mean square error (RMSE) of the position are within 0.2 mm.