Team Delft’s robot winner of the Amazon Picking Challenge 2016

None, None; None, None; None, None; None, None; None, None; None, None; None, None; None, None; None, None; None, None; None, None; None, None; None, None; None, None; None, None; None, None

Team Delft’s robot winner of the Amazon Picking Challenge 2016

Conference Paper (2017)

Author(s)

C. Hernandez Corbato (TU Delft - Mechanical Engineering)

Mukunda Bharatheesha (TU Delft - Mechanical Engineering)

Wilson Ko (Delft Aerial Robotics (DAR))

Hans Gaiser (Delft Aerial Robotics (DAR))

Jethro Tan (TU Delft - Mechanical Engineering)

Kanter van Deurzen (Delft Aerial Robotics (DAR), TU Delft - OLD Computer Aided Design Engineering)

Maarten de Vries (TU Delft - Mechanical Engineering)

Bas Van Mil (TU Delft - RoboValley, Delft Aerial Robotics (DAR))

Jeff van Egmond (TU Delft - Mechanical Engineering)

Ruben Burger (TU Delft - Mechanical Engineering)

Mihai Morariu (TU Delft - Mechanical Engineering)

Jihong Ju

X. Gerrmann

Ronald Ensing (TU Delft - Mechanical Engineering)

Jan Van Frankenhuyzen (TU Delft - Mechanical Engineering, Delft Aerial Robotics (DAR))

Martijn Wisse (Delft Aerial Robotics (DAR), TU Delft - Mechanical Engineering)

Research Group

Robust Robot Systems

Deep learning Motion planning Grasping Warehouse automation Robotic system

DOI related publication

https://doi.org/10.1007/978-3-319-68792-6_51 Final published version

To reference this document use

https://resolver.tudelft.nl/uuid:cb73964d-edd8-473b-a314-db2f0746a6cd

More Info

expand_more

Publication Year

2017

Language

English

Research Group

Robust Robot Systems

Bibliographical Note

Champion Paper

Pages (from-to)

613-624

Publisher

Springer

ISBN (print)

9783319687919

ISBN (electronic)

978-3-319-68792-6

Event

RoboCup 2016: 20th Annual RoboCup International Symposium (2016-06-30 - 2016-07-04), Leipzig, Germany

Downloads counter

520

Abstract

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.