An Industrial Robot Positioning Method Based on Guidance of Multi-Line Structured Light Vision
YU Jun1 , LI Shuanggao1 , LI Gen1 , ZHU Kui2
( 1. College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics & Astronautics, Nanjing 210016, China; 2. Shenzhen JT Automation Equipment Co., Ltd., Shenzhen 5181021, China )
Abstract：In order to realize the three-dimensional positioning function of the industrial robot to target objects with weak texture and no obvious positioning feature points, a multi-line structured light vision guided industrial robot positioning method is proposed and the positioning accuracy is analyzed experimentally. Multi-line structured light measurement module consisting of industrial camera and laser is used as the vision senor of the positioning system. Firstly, a multi-line structured light positioning feature points extraction algorithm based on corner detection is proposed, and the three-dimensional information of feature points is reconstructed by stereo vision principle. Secondly, the reconstructed positioning feature points are registered with the discrete points of the theoretical model, and combined with the calibration parameters, the relative poses of the end are solved. Finally, a closed-loop attitude control system based on pose feedback is established. Experimental results show that the proposed method has high positioning accuracy, and it can meet the requirements of industrial applications.
2020, 
