Computer Vision for Industrial Robot in Planar Bin Picking Application

摘要

This research presents an effectively autonomous method that can save time and increases productivity for an assembly line in industry by using a 6DOF manipulator and computer vision. The objects are flat, aluminum type and randomly stacked in a box. Firstly, 2D color image processing is performed to label the object, then using 3D pose estimating algorithm, the surface normal, angle and position of an object are calculated. To reduce the burden time of 3D pose estimation, a voxel grid filter is implemented to reduce the number of points for the 3D cloud of the objects. As known the 3D image object was obtained by camera in bin often involves both heavy noise and edge distortions, so to prepare for the assembly a manipulator will pick and place it at sub position then a 2D camera is used to estimate the pose of the object correctly. Through implement experiment, the system proved that it is stable and have good precision. Installing time and maintaining is fast and not complicated. It is applicable in production line where mass product is produced. It is also the good foundation for other deep researches.