Carton handling Carton depalletizing by robot and AI

Source: Sick | Translated by AI 2 min Reading Time

Related Vendors

With Palloc, a robot guidance system for "Pallet Content Localization," Sick demonstrates an AI-supported, adaptive localization capability for automatic depalletizing with robots.

With Palloc from Sick, a robot guidance system is now available that can recognize almost any type of carton, allowing the robot to safely detect, grasp, and handle the boxes.(Image: Sick)
With Palloc from Sick, a robot guidance system is now available that can recognize almost any type of carton, allowing the robot to safely detect, grasp, and handle the boxes.
(Image: Sick)

Manual, conventional, or robot-based—multiple concepts often come into question for a palletizing project to ensure the smooth transition of goods from delivery to shipping or further processing, as Sick says. Robot guidance systems played an essential role in conjunction with smart camera systems, artificial intelligence (AI), and deep learning functions, which on the one hand accelerated logistics and production processes and on the other hand could significantly reduce the monotonous burden on employees. The robot guidance system Palloc combines 3D stereo and color image capture with its browser-based user interface. Therefore, it is the most future-proof guidance system for robots currently available because the sensor app of the neural network is directly integrated into the camera. And the smart stand-alone system can be seamlessly implemented into the control of any industrial robot via Ethernet TCP/IP, which also applies to cobots, as Sick emphasizes.

Almost all types of cartons can be safely grasped

The Palloc robot guidance system from Sick allows the localization of almost unlimited variants of stacked cartons on pallets, providing the position coordinates of each carton for reliable and secure robot operation. The system's 3D snapshot camera can be flexibly mounted on the robot gripper or above the detection area. This enables even the smallest features to be reliably detected, independent of the height of the top layer of cartons to be picked. The camera delivers up to 30 full-frame and high-resolution color images and 3D image pairs per second. According to Sick, these 3D values, which are automatically calculated with the contrast values of the color data, ensure that contours, edges, and layer heights of packages are captured and measured very precisely and reproducibly. Furthermore, the pre-installed neural network is factory-trained with a variety of carton types of different sizes, colors, designs, and prints. If needed, new carton variants can be added at any time using Sick's user-friendly AI tool suite – such as the Sick Webservice d-Studio for training neural networks.

Subscribe to the newsletter now

Don't Miss out on Our Best Content

By clicking on „Subscribe to Newsletter“ I agree to the processing and use of my data according to the consent form (please expand for details) and accept the Terms of Use. For more information, please see our Privacy Policy. The consent declaration relates, among other things, to the sending of editorial newsletters by email and to data matching for marketing purposes with selected advertising partners (e.g., LinkedIn, Google, Meta)

Unfold for details of your consent