High-precision robotic assembly system using three-dimensional vision

The design of a high-precision robot assembly system is great challenge. In this article, robotic developed to assemble two components with six degree-of-freedoms in three-dimensional space. It consists manipulators, structured light camera which mounted on the end-effector aside component A measure pose B. Firstly, features irregular are extracted based U-NET network training few labeled images. Secondly, an algorithm proposed calculate B image and corresponding coordinates its ellipse surface. Thirdly, errors including position one orientation error space, Cartesian space computed control motions align hybrid visual servoing method used system. experimental results verify effectiveness designed