Calibration Method Based on Models and Least-Squares Support Vector Regression to Enhance Robot Positioning Accuracy

The positioning accuracy of a robot directly affects the quality of its operations. In this study, a calibration method is proposed based on combining a model with least-squares support vector regression (LSSVR) to improve robot positioning accuracy. First, a geometric error model of the robot is established. Second, singular value decomposition (SVD) and physical model analysis method are employed to process the coupling parameters in the error model to improve the accuracy and efficiency of identification. Third, as nongeometric errors hinder the construction of an accurate and complete mathematical model and affect the residual positioning errors of the robot, LSSVR is used to compensate for the residual positioning errors caused by nongeometric errors. The proposed method thus improves the accuracy and robustness of finite sample estimation. Finally, an experiment is performed on an IRB1410 robot with a parallelogram mechanism. The maximum/mean positioning errors of the robot decrease from 2.0348/1.0978 mm to 0.1659/0.0733 mm, and the effectiveness of the proposed method is verified. The proposed method has higher prediction accuracy and stability for small samples than other methods.