Automatic Teaching of Welding Robot for 3-Dimensional Seam Based on Ant Colony Optimization Algorithm

The research work of this paper concentrates on 3-dimensional seam detection based on stereovision technique and the optimal control of weld torch attitude based on ant colony optimization algorithm during the automatic teaching of welding robot. A binocular stereovision system with a small linear laser emitter is designed to detect seam position and its orientation, and an ant colony optimization algorithm based on the discretization of the angle increment of robot joint is presented and a pheromone updating strategy is proposed. For the computation of weld torch attitude, the coordinate transformation matrices of a welding robot with 6 degrees-of-freedom are given. The experimental results for curvilinear seams and saddle-shaped seams show that the automatic teaching of welding robot can be successfully completed based on ant colony optimization algorithm using the 3-dimensional seam data acquired by stereovision detection, and the welding trajectory generated by the proposed method has higher accuracy compared with conventional proportional-integral-differential controller and fuzzy controller.