Automated unloading and palletizing method based on computer vision and robot control

Abstract

The application discloses an automatic unloading and stacking method based on computer vision and robot control, and belongs to the technical field of intelligent logistics automation. The method innovatively installs a depth camera on the first rotating joint of an unloading and stacking robot mechanical arm, and combines a hard trigger acquisition mechanism to realize "non-stop visual guidance". In the unloading link, a template-free instance segmentation and point cloud geometric fitting method is adopted to directly calculate the pose and size of unknown cartons, and DBSCAN spatial clustering is used for global safety planning. In the stacking link, seamless monitoring is realized through back-to-back double cameras, and a stacking scheme is dynamically generated in combination with an adaptive algorithm. The application effectively solves the problems of dependence on templates and markers, insufficient operation safety and slow system beat of the prior art, and realizes efficient, safe and universal full-process automatic operation.

Images