Autonomous weld seam identification and localisation using eye-in-hand stereo vision for robotic arc welding

One of the main difficulties in using robotic welding in low to medium volume manufacturing or repair work is the time taken to programme the robot to weld a new part. It is often cheaper and more efficient to weld the parts manually. This paper presents a method for the automatic identification and location of welding seams for robotic welding using computer vision. The use of computer vision in welding faces some difficult challenges such as poor contrast, textureless images, reflections and imperfections on the surface of the steel such as scratches. The methods developed in the paper enables the robust identification of narrow weld seams for ferrous materials combined with reliable image matching and triangulation through the use of 2D homography. The proposed algorithms are validated through experiments using an industrial welding robot in a workshop environment. The results show that this method can provide a 3D Cartesian accuracy of within ±1 mm which is acceptable in most robotic arc welding applications.