Publications / 2024 Proceedings of the 41st ISARC, Lille, France

Fast-Pixel-Matching Algorithm for Automated Shear Stud Welding Based on the Integration of 2D Drawings and Structured Light Cameras

Huiguang Wang, Lu Deng, Ran Cao, Jingjing Guo
Pages 168-176 (2024 Proceedings of the 41st ISARC, Lille, France, ISBN 978-0-6458322-1-1, ISSN 2413-5844)
Abstract:

Due to the lack of depth information, using 2D drawings to guide robotic manufacturing is difficult, such as stud welding and drilling. In this paper, a new algorithm, Fast-Pixel-Matching (FPM), is proposed to provide depth information for precise point positioning based on 2D drawings and structured light cameras. Based on our experiment, the efficiency of the FPM process is found to be at least 20 times higher than the brute-force search (BFS) method. Also, we demonstrated that the algorithm can be applied to automated stud welding, where the efficiency of positioning can be significantly improved and the positioning accuracy of the proposed method meets the code requirements.

Keywords: Point positioning, 2D drawings, Supplementation of depth information, Stud welding, 3D vision