High-precision hand-eye calibration method for garbage sorting robot

Abstract

The invention discloses a high-precision hand-eye calibration method for a garbage sorting robot, which is suitable for an eye-to-hand system of a parallel robot, and the system is composed of a visual module, a robot module and a transmission module. Comprising the following steps: (1) solving camera parameters and an attitude matrix; (2) solving a camera internal reference matrix and a distortion matrix, and completing conversion between a pixel coordinate system and a camera coordinate system; (3) performing mapping transformation by using a mapiage operator to eliminate distortion, and obtaining a corrected reference plane image; (4) solving external parameters of the camera, and completing conversion between a camera coordinate system and a corresponding world coordinate system; and (5) performing conversion from the world coordinate system to the robot coordinate system by adopting a nine-point calibration method. According to the invention, camera distortion elimination, camera internal and external parameter calibration and robot calibration are organically combined, calibration errors are reduced, and the calibration precision is controlled to be 0.1 mm.

Description

technical field [0001] The invention relates to the technical field of robot hand-eye calibration methods, in particular to a high-precision hand-eye calibration method for garbage sorting robots. Background technique [0002] As the proportion of recyclables such as PET, PE and other plastics in domestic waste increases year by year, traditional methods such as incineration and landfill have high disposal costs and a heavy burden on the environment; currently, most of the recycling methods for domestic waste are manual Sorting, the working environment of workers is harsh, and the efficiency of manual sorting is low and the error rate is high. Therefore, the automatic sorting of recyclables in domestic waste based on artificial intelligence and robot technology has revolutionary significance for the renewable resource industry. [0003] Existing automated sorting generally uses six-axis industrial robots instead of manual operations, but its repeat positioning accuracy is l...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a high-precision hand-eye calibration method for garbage sorting robots, which solves the problem of low calibration accuracy and poor material grasping caused by camera lens distortion in the existing eye-to-hand parallel robot calibration method Problem: By organically combining the elimination of camera distortion with camera internal and external reference calibration and robot calibration, the calibration error is greatly reduced, thereby achieving a calibration accuracy of 0.1mm

Images