An Inspection Robot for Detecting and Tracking Welding Seam

Abstract

The paper introduces a new inspection robotic system for effectively detecting and tracking welding seam on a metal surface. Frequently inspecting and assessing conditions of weld joints are critical in many ageing infrastructures. Given advancement in the robotic research, it is proposed to develop an autonomous inspection system where a robot with an embedded camera sensor is used to conduct the inspections. More specifically, images of a metal surface are in situ captured and then processed by exploiting the state-of-the-art computer vision algorithms, which results in location of the weld on the corresponding surface. Information of the welding seam is then forwarded to the controllers of the robot to accurately drive it along the weld. Moreover, the wheels of the robot are fabricated with magnets that allows it to operate on different surfaces positioned at different inclination angles. The fully developed robot was experimentally evaluated in a real-world welded steel plate, where the obtained results are highly promising.