作者: Max Schwarz , Anton Milan , Christian Lenz , Aura Munoz , Arul Selvam Periyasamy
DOI: 10.1109/ICRA.2017.7989348
关键词: Motion (physics) 、 Information retrieval 、 Automation 、 Engineering 、 Support vector machine 、 Domain (software engineering) 、 Object detection 、 Variety (cybernetics) 、 Engineering drawing 、 Segmentation 、 Feature extraction
摘要: Part handling in warehouse automation is challenging if a large variety of items must be accommodated and are stored unordered piles. To foster research this domain, Amazon holds picking challenges. We present our system which achieved second third place the Picking Challenge 2016 tasks. The challenge required participants to pick list from shelf or stow into shelf. Using two deep-learning approaches for object detection semantic segmentation one item model registration method, localizes requested item. Manipulation occurs using suction on points determined heuristically 6D registration. Parametrized motion primitives chained generate motions. full-system evaluation during APC component-level evaluations perception an annotated dataset.