Abstract
Automated Item Picking (AIP) systems can be used to improve the quality of order picking processes and to reduce the cost. This work presents an AIP solution for the sports and fashion sector. The system consists of an industry robot, a customized gripper and an AI-based perception. A convolutional neural network is trained for identification and localization of various apparel articles and shoeboxes under real conditions.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2019 Moritz Weisenböhler, Michael Walz, Christian Wurll