This paper describes Team Delft’s robot, which won the Amazon Picking Challenge 2016, including both the Picking and the Stowing competitions. The goal of the challenge is to automate pick and place operations in unstructured environments, specifically the shelves in an Amazon warehouse. Team Delft’s robot is based on an industrial robot arm, 3D cameras and a customized gripper. The robot’s software uses ROS to integrate off-the-shelf components and modules developed specifically for the competition, implementing Deep Learning and other AI techniques for object recognition and pose estimation, grasp planning and motion planning. This paper describes the main components in the system, and discusses its performance and results at the Amazon Picking Challenge 2016 finals.

Recently, robots are making their way towards the small and medium enterprises at a quick pace. This is due to market demand and enabled by reduction in costs of robot systems. If robots can be introduced strategically in existing production workflows, productivity could be increased. However, the task division and interaction between human and robot co-workers need to be optimized in order to achieve this. This work-in-progress paper presents a pilot setup to explore such scenarios. We discuss early findings and we present our vision for the future of human robot coproduction.