Photoneo depalletizer is a smart automation solution for unloading pallets laden with boxes using artificial intelligence. This is achieved by combining in-house developed 3D machine vision with large scanning volume - Photoneo PhoXi 3D Scanner - and advanced machine learning algorithms trained and tested for more than 5000 types of boxes. AI trained on a huge dataset immediately recognizes each box and sends a command to the robot. Using a specially developed universal gripper, the robot performs the picking action with an accuracy of +-3 mm. This way it is able to unload 1000 boxes in one hour, with 99.7 % pick rate accuracy. Photoneo depalletizer helps to reduce throughput, increase productivity and safety, and ultimately save costs.
Innovation: In contrast to delayerization, where the robot picks the whole pallet with uniform, neatly stacked boxes of the same height, and as opposed to the classic depalletization, Photoneo AI-powered depalletization is based on smart machine learning algorithms. The solution presents a higher level of unloading pallets and as such offers numerous advantages.
It requires a smaller placement area than delayerization (comprising the size of the largest box in contrast to the whole pallet) and also a smaller robot and a smaller gripper as it needs to handle a lighter payload. Despite the fact that the gripper is smaller, it is able to pick boxes of up to 50 kg. These advantages lead to another great benefit - significant cost savings.
One of the features that distinguishes Photoneo AI-powered depalletizer from classic depalletization solutions is the sophisticated machine learning algorithm that constantly learns and recognizes new types of boxes, be they of different shapes, sizes or material. Shiny, reflecting or black surfaces, varying texture, patterns or pictures that “mislead” the 3D vision, tapes coming unstuck, or boxes packed so tightly that it is difficult to recognize the gap that separates them (be it as thin as 0,5 millimeters) or to differentiate it from a line contouring the opening of one particular box - these are major challenges that Photoneo depalletizer overcomes. The boxes do not need to be stacked in patterns but can be placed randomly, even tilted at an angle, and the robot is still able to pick them. Photoneo depalletizer uses the most advanced way to segment the individual boxes on the basis of texture and 3D data - a convolutional neural network (CNN).
Another distinguishing feature is the superior 3D vision enabled by Photoneo PhoXi 3D Scanner. The scanning volume of the deployed 3D scanner needs to be large enough to scan the whole pallet from sufficient distance - taking into consideration the minimum space required for robotic manipulation, the scanner generally needs to be mounted approximately 3 - 4 meters above the pallet. The PhoXi 3D Scanner combines a large scanning volume on the one hand and high resolution and accuracy on the other.
Finally, there is yet another significant feature that distinguishes the Photoneo solution from others - and that is its universality. It works out of the box, without necessitating any training of the system. If it comes across new types of boxes, the system is able to retrain itself. Its universality also leads to short deployment and integration time and supports Photoneo endeavor to be compatible with any major robotic brand.