Author(s)

Chao Xu, Ying Sun, and Jinrong Tian

Corresponding Author

Chao Xu

Abstract

As the final step of metal cutting, the grinding and polishing process determines the surface quality and precision of the workpiece to be processed to a large extent. With the improvement of the intelligent degree of manufacturing industry, intelligent manufacturing equipment with adaptability and certain learning behaviors is the trend of future factories. Considering the low efficiency and large error of manual grinding and polishing, a grinding and polishing manipulator control method based on Kinect three-dimensional reconstruction is proposed. First, a depth map of the surface of the workpiece to be polished is obtained using a Kinect depth camera, and a series of processes are performed to obtain accurate surface information of the workpiece to be polished. Then the obtained information is compared with the ideal model of the 3D software. The n sets of parallel planes are intersected with the coincident model. Finally, the improved section method is used to determine the trajectory of the grinding and polishing manipulator, so as to achieve the purpose of grinding and polishing manipulator control.

Keywords

Kinect, Point cloud data, Grinding and polishing robot, Path planning