An approach to robot welding path autonomous planning of the intersection weldment based on 3D visual perception

To improve the accuracy, an approach to robot welding path planning of the intersection weldment based on 3D visual perception is proposed. It adopts the two-stage location scheme of "global 3D reconstruction + local scanning correction". First, this paper proposes an improved K-means clustering method based on the geometric features of workpiece point-cloud, to achieve accurate and fast point-cloud segmentation. Second, the intersection parameters of workpiece can be quickly calculated by the proposed parameter identification method. Third, this paper plans the scanning path of laser scanner according to the identified parameters, and puts forward an algorithm of weld path points recognition combined with the actual weldments state. Then, the pose of robot welding torch is obtained by using spline fitting algorithm and welding torch attitude estimation algorithm. Finally, the experiments show the path planning error is about 0.3 mm, which has increased a lot than the published methods.