direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Amazon Picking Challenge 2015


In May 2015, our Team RBO won a prestigious international robotics challenge, the Amazon Picking Challenge [1]. This challenge aims to solve one of the last problems in warehouse automation: identifying and grasping objects from a warehouse shelf.

The goal of the competition was to develop a robotic system with the ability to fulfill a fictitious order by autonomously picking the ordered items from a shelf. The competition posed a set of challenging problems: the robot had to visually perceive and grasp a wide variety of objects; the exact position in each bin of the shelf was not known beforehand; and the robot had to act fully autonomously, without any human intervention being allowed.

Our robot was able to secure the lead by picking 10 out of 12 objects, outperforming 25 teams from Europe, USA and Asia, amongst them teams from the Massachusetts Institute of Technology (MIT), UC Berkeley as well as many robotics companies.

Video material

Official summary video by Amazon: http://www.amazonpickingchallenge.org/ [2] 

Our run, sped by 4x: https://youtu.be/DuFtwpxQnFI [3]

Our run, original speed: https://youtu.be/UrpMfdj-Mpc [4]

Video showing the perception algorithm running on our robot: https://youtu.be/TsVUQtRNIts [5]

Interview with Sebastian at the Deutscher Logistik Kongress [6] (in German): https://www.youtube.com/watch?v=d5yjIw3D9JQ  [7]

Press coverage

International (english)

Engadget: http://www.engadget.com/2015/06/01/amazon-picking-challenge-winner/ [8]

RoboHub: http://robohub.org/team-rbo-from-berlin-wins-amazon-picking-challenge-convincingly/ [9]

Slashdot: http://hardware.slashdot.org/story/15/06/02/2355212/building-amazon-a-better-warehouse-robot [10]

Amazon watchblog: https://www.amazon-watchblog.de/technik/271-tu-berlin-picking-challenge-amazon.html [11]

The Economist: http://www.economist.com/news/science-and-technology/21653599-how-combine-man-and-machine-without-creating-cyborg-handy-collaborator [12]


Wirtschaftswoche: http://www.wiwo.de/unternehmen/handel/amazon-roboter-veraendern-die-zukunft-des-onlinehandels/11843744.html [13]

Heise online: http://www.heise.de/newsticker/meldung/Robotik-Team-der-TU-Berlin-gewinnt-Amazons-Picking-Challenge-2677698.html [14]

Telepolis: http://www.heise.de/tp/artikel/46/46921/1.html [15]

Logistik heute: http://www.logistik-heute.de/Logistik-News-Logistik-Nachrichten/Markt-News/13136/Robotics-and-Biology-Laboratory-der-TU-Berlin-besiegt-Forschungsinstitut-MIT [16]

Relevant publications

Clemens Eppner, Sebastian Höfer, Rico Jonschkowski, Roberto Martín-Martín, Arne Sieverling, Vincent Wall and Oliver Brock. Four aspects of building robotic systems: lessons from the Amazon Picking Challenge 2015 [17]. Autonomous Robots. Springer US 42(7):1459–1475, 2018.

Clemens Eppner, Sebastian Höfer, Rico Jonschkowski, Roberto Martín-Martín, Arne Sieverling, Vincent Wall and Oliver Brock. Lessons from the Amazon Picking Challenge: Four Aspects of Robotic Systems Building [18]. Robotics: Science and Systems (RSS), 2016.

Rico Jonschkowski, Clemens Eppner, Sebastian Höfer, Roberto Martín-Martín, Oliver Brock. Probabilistic Multi-Class Segmentation for the Amazon Picking Challenge [19]. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016.

Rico Jonschkowski, Clemens Eppner, Sebastian Höfer, Roberto Martín-Martín, Oliver Brock. Probabilistic Multi-Class Segmentation for the Amazon Picking Challenge [20]. Technical Report RBO-2016-01 , Department of Computer Engineering and Microelectronics, Technische Universität Berlin, 2016.

Nikolaus Correll, Kostas E. Bekris, Dmitry Berenson, Oliver Brock, Albert Causo, Kris Hauser, Kei Okada, Alberto Rodriguez, Joseph M. Romano, Peter R. Wurman. Lessons from the Amazon Picking Challenge [21]. arXiv:1601.05484 [cs.RO]. 2016

Colin Rennie, Rahul Shome, Kostas E. Bekris, Alberto F. De Souza: A Dataset for Improved RGBD-based Object Detection and Pose Estimation for Warehouse Pick-and-Place [22]. arXiv:1509.01277 [cs.CV]. 2016

------ Links: ------

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions

Copyright TU Berlin 2008