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.
@article{arxiv.1610.05514,
title = {Team Delft's Robot Winner of the Amazon Picking Challenge 2016},
author = {Carlos Hernandez and Mukunda Bharatheesha and Wilson Ko and Hans Gaiser and Jethro Tan and Kanter van Deurzen and Maarten de Vries and Bas Van Mil and Jeff van Egmond and Ruben Burger and Mihai Morariu and Jihong Ju and Xander Gerrmann and Ronald Ensing and Jan Van Frankenhuyzen and Martijn Wisse},
journal= {arXiv preprint arXiv:1610.05514},
year = {2016}
}