Advertisement

Team Delft’s Robot Winner of the Amazon Picking Challenge 2016

  • Carlos Hernandez
  • Mukunda Bharatheesha
  • Wilson Ko
  • Hans Gaiser
  • Jethro Tan
  • Kanter van Deurzen
  • Maarten de Vries
  • Bas Van Mil
  • Jeff van Egmond
  • Ruben Burger
  • Mihai Morariu
  • Jihong Ju
  • Xander Gerrmann
  • Ronald Ensing
  • Jan Van Frankenhuyzen
  • Martijn Wisse
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9776)

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.

Keywords

Robotic system Warehouse automation Motion planning Grasping Deep learning 

Notes

Acknowledgements

All authors gratefully acknowledge the financial support by the European Union’s Seventh Framework Programme project Factory-in-a-day (FP7-609206) We would like to thank RoboValley (http://www.robovalley.com), the ROS-Industrial consortium, our sponsors Yaskawa, IDS, Phaer, Ikbenstil and Induvac, the people at the Delft Center for Systems and Control and TU Delft Logistics for their support, also Lacquey B.V. for helping us handle our heavy rail, and finally special thanks to Gijs vd. Hoorn for his help during the development of the robotic system.

References

  1. 1.
    Beeson, P., Ames, B.: TRAC-IK: an open-source library for improved solving of generic inverse kinematics. In: Proceedings of the IEEE RAS Humanoids Conference, Seoul, Korea, November 2015Google Scholar
  2. 2.
    Bohren, J.: SMACH (2016). http://wiki.ros.org/smach
  3. 3.
    Correll, N., Bekris, K.E., Berenson, D., Brock, O., Causo, A., Hauser, K., Okada, K., Rodriguez, A., Romano, J.M., Wurman, P.R.: Lessons from the amazon picking challenge. CoRR abs/1601.05484 (2016)Google Scholar
  4. 4.
    Delft Robotics, B.V. http://www.delftrobotics.com/
  5. 5.
  6. 6.
    Mellado, N., Aiger, D., Mitra, N.J.: Super 4PCS fast global pointcloud registration via smart indexing. Comput. Graph. Forum 33(5), 205–215 (2014)CrossRefGoogle Scholar
  7. 7.
    Quigley, M., Conley, K., Gerkey, B.P., Faust, J., Foote, T., Leibs, J., Wheeler, R., Ng, A.Y.: ROS: an open-source robot operating system. In: ICRA Workshop on Open Source Software (2009)Google Scholar
  8. 8.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NIPS) (2015)Google Scholar
  9. 9.
  10. 10.
    Sucan, I.A., Chitta, S.: MoveIt!. http://moveit.ros.org
  11. 11.
    TUD Robotics Institute. http://robotics.tudelft.nl

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Carlos Hernandez
    • 1
  • Mukunda Bharatheesha
    • 1
  • Wilson Ko
    • 2
  • Hans Gaiser
    • 2
  • Jethro Tan
    • 1
  • Kanter van Deurzen
    • 2
  • Maarten de Vries
    • 2
  • Bas Van Mil
    • 2
  • Jeff van Egmond
    • 1
  • Ruben Burger
    • 1
  • Mihai Morariu
    • 2
  • Jihong Ju
    • 1
  • Xander Gerrmann
    • 1
  • Ronald Ensing
    • 2
  • Jan Van Frankenhuyzen
    • 1
  • Martijn Wisse
    • 1
    • 2
  1. 1.Robotics InstituteDelft University of TechnologyDelftThe Netherlands
  2. 2.Delft Robotics, B.V.DelftThe Netherlands

Personalised recommendations