A Calibration Optimization Method for a Welding Robot Laser Vision System Based on Generative Adversarial Network

The accuracy and efficiency of a calibration process have a great influence on the robot locating accuracy. In the welding robot laser vision system discussed in this article, traditional structured light and hand–eye calibration methods are complex and time consuming. They require many manually collected labeled data, which leads to low calibration efficiency and accuracy. To solve the above problems, a calibration optimization method for the welding robot laser vision system based on the generative adversarial network is proposed in this article. By establishing an accurate calibration model, the calibration process is transformed into an optimization problem for the calibration parameters. An efficient and intelligent collection method is adopted to provide accurate, diverse, and sufficient calibration data for the calibration optimization method. The experimental results verify that the proposed method greatly improves the efficiency of calibration data collection. The reference point positioning experiment demonstrates that our method has low uncertainty in point positioning. The tracking experiments prove that our method keeps good accuracy and robustness in the tracking system, especially when the welding robot’s pose changes greatly and the tracking trajectory is complex and changeable.