Research on accuracy range of shaft-hole assembly with robot based on image recognition

In this paper, the automatic assembly of shaft-hole with robot is researched, and the accuracy range of robot shaft -hole assembly based on image recognition algorithm is explored. According to the accuracy experiment requirements, the robot system and shaft-hole assembly platform are built, the eye-in-hand system calibration scheme is designed. A recognition algorithm combining image preprocessing technology, edge detection and Hough transform circle detection is proposed to locate the mounting hole and realize the shaft-hole assembly with the robot. In order to improve the image recognition process, image preprocessing technologies such as gray level processing, Gaussian filter are used to reduce the influence of the surrounding environment and noise points. Edge detection with Sobel operator is adopted to enhance the target features of the image and improve the accuracy of circle center recognition. Hole center coordinates is obtained by Hough transform circle detection. Finally, the hand-eye relationship obtained by calibration is used to drive the robot to realize the shaft-hole assembly. In order to obtain the accuracy range of shaft-hole assembly, several experiments were carried out, and the experimental results showed that the error of shaft-hole assembly is limited to ±1 mm.