At present, aluminum plates are widely used in aerospace, machinery, and other fields because of their light weight, good manufacturability, and strong corrosion resistance. However, during long-term use, defects that will affect the structural strength such as cracks are easy to appear. Therefore, it is necessary to conduct automatic non-destructive testing of large metal plates to determine the location, size, and structural damage to their defects. Compared with manual detection, automated detection has many advantages such as high detection efficiency, high repeatability, strong flexibility, and low labor intensity. Based on the spinor theory, this paper uses the product of exponentials (POE) to model the kinematics of the Aubo-i5 manipulator and obtain the positive kinematics equations, which are compiled by analytic geometry and algebraic methods combined with Paden-Kahan subproblems and matrix theory. The inverse kinematics algorithm of the 6R manipulator is based on this model. An automated non-destructive testing system including a robotic arm and ultrasonic phased array testing equipment was built. At the same time, a robotic arm simulation platform was built based on ROS, and the inverse kinematics algorithm was used to control the robotic arm through the MoveIt!. The angle error can be controlled within 2.5°.

In the actual production measurement process, the vision of machine vision is to broaden the application scene of surface structured light and realize the surface measurement and detection of large parts. This paper introduces a 3D image mosaic system based on fringe projection. The sensor system is composed of a DLP projector and a 3D camera, and is fixed at the end of the robot arm. The three-dimensional point cloud data of the workpiece surface to be measured is obtained by moving the manipulator and using the raster projection method. An algorithm of rough positioning using manipulator is proposed, and the automobile splicing experiment is carried out. Experimental results show that this method can effectively obtain 3D point cloud data and has good stitching accuracy.