Fast Object Learning and Dual-arm Coordination for Cluttered Stowing, Picking, and Packing

摘要: Robotic picking from cluttered bins is a demanding task, for which Amazon Robotics holds challenges. The 2017 Challenge (ARC) required stowing items into storage system, specific items, and packing them boxes. In this paper, we describe the entry of team NimbRo Picking. Our deep object perception pipeline can be quickly efficiently adapted to new using custom turntable capture system transfer learning. It produces high-quality item segments, on grasp poses are found. A planning component coordinates manipulation actions between two robot arms, minimizing execution time. has been demonstrated successfully at ARC, where our reached second places in both task final stow-and-pick task. We also evaluate individual components.