Calibration of Cartesian robot based on machine vision

Machine vision makes robots more intelligent, but most Cartesian robots rely on manual programming to perform operations. This paper presents a new nine points calibration method for Cartesian robot based on machine vision, and realizes the automatic assembly of Cartesian robot. Firstly, affine transformation model of Cartesian robot was established. The homogeneous matrices of four affine transformations formed a closed chain. Secondly, the HALCON image processing technique was used to extract the image coordinates of the center points of interest and record the current mechanical coordinates. Thirdly, through the obtained image coordinates and mechanical coordinates, the transformation relationship between the self-made calibration board and the basic coordinate system was obtained. Finally, the effectiveness of the calibration proposed in this paper was validated through case study.