A kinematic calibration method for robots based on the PGTF error model and Levenberg-Marquardt algorithm

Robots use motors for power output and realize joint motion through reducers and mechanical transmissions, which affect the absolute positioning accuracy. In view of this problem, an error model based on Preprocessing-Geometric-Transmission-Flexibility (PGTF) is proposed and solved by Levenberg-Marquardt algorithm. First, the theoretical kinematic model is established by MD-H model method. Second, the data was pre-processed in dimension upgrade and the robot error identification model was established for geometric error, transmission error and flexible error. Third, Levenberg-Marquardt algorithm was used to find the global convergence solution to realize the identification of error parameters, and the actual robot kinematic model was compensated. Finally, the experiment is carried out on the real robot machine. Through theoretical analysis and verification of real machine data, the average error of kenbei-5kg robot is reduced from 6.8787 mm to 0.1267 mm, the positioning accuracy is improved by 98.16%, the accuracy compensation algorithm is accurate, and the compensation effect is remarkable.