Automated robotic welding based on teaching and visual correction

A method combining teaching and visual correction for weld seam tracking is presented to realize robotic automatic welding. In this method, a laser-based vision sensor is applied to traditional teaching and playback welding robot to measure deviations between the teaching path and the real path, then the robot controller adjusts the moving direction and position of the welding torch according to the deviations and teaching path, hence the seam tracking function can be fulfilled. Experiments have been conducted with an experimental system consisting of a 6-DOF robot and a laser-based vision sensor, and the experimental results demonstrate the validity of the proposed method.