Vision-based construction robot for real-time automated welding with human-robot interaction

The construction industry is a major consumer of steel, with welding being a crucial aspect of steel fabrication. However, a shortage of welders has emerged as a significant issue. Therefore, the ultimate goal of this study is to develop a fully automated mobile robotic welding system. The preliminary paper presented a method for the automatic detection and alignment of various welding joints. Building on this, this paper proposes a real-time automated welding system capable of path planning and tracking for two butt joints using visual data. Given the precision required in welding, two robotic operations were devised: one for following a trajectory based on real-time image data, and another for welding guided by laser-scanned data. Additionally, human-robot interaction is proposed for path planning in cases where deep learning-based joint detection fails. The automated robotic welding was performed to test the performance of the proposed system, demonstrating its effectiveness and accuracy.