A Vision Algorithm for Robot Seam Tracking Based on Laser Ranging

In automatic welding processing, high temperature likely induces local deformation of the weldment, resulting in accuracy deviation and welding quality. Therefore, the research on weld tracking technology is significant. Most current weld trackers are installed at the end of the welding torch. Due to the tracker volume, interference often occurs in welding operations under complex conditions. This paper designs and develops a seam tracking system for human-computer interactive mobile robots. The spatial coordinates were obtained by camera calibration, line laser calibration, and hand-eye calibration. The seam feature points are extracted by image processing. A seam tracking experimental platform is built, and the results are compared with the seam's actual fitting curve to verify the system's feasibility.