A Coaxial Vision Assembly Algorithm for Un-centripetal Holes on Large-scale Stereo Workpiece Using Multiple-DOF Robot

摘要

Peg-in-hole assembly focuses on the alignment of hole and peg in industry. However, un-centripetal holes on a complex stereo workpiece are still assembled mainly by human. A combination method with robotic alignment and coaxial machine vision is generated to assist the monocular camera to make visual alignment. Multi-DOF robot is employed to adjust the positions and attitudes of each un-centripetal hole. The algorithm converts the alignment of holes on the complex-shaped workpiece to coaxial vision alignment. The principle and configuration of the alignment system are presented. The algorithm using robot kinematics to adjust the assembly holes and the alignment algorithm for vision system is introduced with experiments. The results show that this algorithm can align the axis of the un-centripetal holes, providing a good condition for vision recognizing with monocular vision system. This paper lays a good foundation of employing precise coaxial vision system in industry for un-centripetal hole and stereo workpiece.