Advertisement

What Happened at the DARPA Robotics Challenge Finals

  • Christopher G. Atkeson
  • P. W. Babu Benzun
  • Nandan Banerjee
  • Dmitry Berenson
  • Christoper P. Bove
  • Xiongyi Cui
  • Mathew DeDonato
  • Ruixiang Du
  • Siyuan Feng
  • Perry Franklin
  • M. Gennert
  • Joshua P. Graff
  • Peng He
  • Aaron Jaeger
  • Joohyung Kim
  • Kevin Knoedler
  • Lening Li
  • Chenggang Liu
  • Xianchao Long
  • T. Padir
  • Felipe Polido
  • G. G. Tighe
  • X. Xinjilefu
Chapter
Part of the Springer Tracts in Advanced Robotics book series (STAR, volume 121)

Abstract

This paper summarizes observations and lessons learned by the WPI-CMU team and self-reports made by many of the DARPA Robotics Challenge teams on what happened at the DARPA Robotics Challenge Finals. Major conclusions are: (1) Reducing operator errors is the most cost effective way to improve robot performance. Methods include operator training and practice, and software safeguards to detect and prevent operator errors. (2) Super-human sensing is another way to greatly improve robot performance. To some extent this matches what happened in the DARPA autonomous driving challenges, in which improved sensing was the key to improved performance. (3) Paradigm shifts are needed in academic robotics, such as emphasizing designing robust behaviors, systems design including what seem like unimportant issues such as thermal management, and consistent real world results rather than videos of the rare successes.

Notes

Acknowledgements

This paper is an extended version of a conference paper (Atkeson et al. 2015), and is based upon work supported in part by the DARPA Robotics Challenge program under DRC Contract No. HR0011-14-C-0011.

References

  1. Atkeson, C. G. (2015). Big Hero 6: Let’s Build Baymax. Retrieved from http://www.build-baymax.org.
  2. Atkeson, C. G. (2017). Robot skin. Retrieved from http://www.cs.cmu.edu/~cga/skin.
  3. Atkeson, C. G., Babu, B. P. W., Banerjee, N., Berenson, D., Bove, C. P., Cui, X., et al. (2015). No falls, no resets: Reliable humanoid behavior in the DARPA Robotics Challenge. In 15th IEEE-RAS International Conference, Humanoid Robots (Humanoids).Google Scholar
  4. Crow, S. (2015). 7 things we learned after the DARPA Robotics Challenge Finals. Retrieved from http://www.roboticstrends.com/article/7_things_you_should_know_after_the_darpa_robotics_challenge_finals.
  5. DARPA. (2015). A celebration of risk (a.k.a., robots take a spill). Retrieved from https://www.youtube.com/watch?v=7A_QPGcjrh0.
  6. DeDonato, M., Dimitrov, V., Du, R., Giovacchini, R., Knoedler, K., Long, X., et al. (2015). Human-in-the-loop control of a humanoid robot for disaster response: A report from the DARPA Robotics Challenge Trials. Journal of Field Robotics, 32(2), 275–292.CrossRefGoogle Scholar
  7. DRC-Teams. (2015). What happened at the DARPA Robotics Challenge? Retrieved from www.cs.cmu.edu/~cga/drc/events.
  8. Dzieza, J. (2015). Behind the scenes at the final DARPA Robotics Challenge: The robots at the final DARPA challenge have come a long way, but they still need a lot of human help. Retrieved from http://www.theverge.com/2015/6/12/8768871/darpa-robotics-challenge-2015-winners.
  9. Gaudin, S. (2015). Separating science fact from science fiction in robotics. Retrieved from http://www.computerworld.com/article/2939331/robotics/separating-science-fact-from-science-fiction-in-robotics-with-video.html.
  10. IEEE Spectrum. (2015). A compilation of robots falling down at the DARPA Robotics Challenge. Retrieved from https://www.youtube.com/watch?v=g0TaYhjpOfo.
  11. IHMC. (2015). Personal communication.Google Scholar
  12. Lumelsky, V. (2015). Home page. Retrieved from http://directory.engr.wisc.edu/me/faculty/lumelsky_vladimir.
  13. MIT. (2015a). Personal communication.Google Scholar
  14. MIT. (2015b). Egress robustness tests. Retrieved from https://www.youtube.com/watch?v=F5CBRmDQXTk.
  15. Mordatch, I., Todorov, E., & Popovic, Z. (2012). Discovery of complex behaviors through contact-invariant optimization. ACM Transactions on Graphics, 31(4), 43:1–43:8.CrossRefGoogle Scholar
  16. Schulman, J., Lee, A., Awwal, I., Bradlow, H., & Abbeel, P. (2013). Finding locally optimal, collision-free trajectories with sequential convex optimization. In Robotics: Science and Systems (RSS). Berlin, Germany.Google Scholar
  17. Sofge, E. (2015). The DARPA Robotics Challenge was a bust. Retrieved from http://www.popsci.com/darpa-robotics-challenge-was-bust-why-darpa-needs-try-again.

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Christopher G. Atkeson
    • 1
  • P. W. Babu Benzun
    • 2
  • Nandan Banerjee
    • 2
  • Dmitry Berenson
    • 2
  • Christoper P. Bove
    • 2
  • Xiongyi Cui
    • 2
  • Mathew DeDonato
    • 2
  • Ruixiang Du
    • 2
  • Siyuan Feng
    • 1
  • Perry Franklin
    • 2
  • M. Gennert
    • 2
  • Joshua P. Graff
    • 2
  • Peng He
    • 2
  • Aaron Jaeger
    • 2
  • Joohyung Kim
    • 1
  • Kevin Knoedler
    • 3
  • Lening Li
    • 2
  • Chenggang Liu
    • 1
  • Xianchao Long
    • 2
  • T. Padir
    • 2
  • Felipe Polido
    • 1
    • 2
  • G. G. Tighe
    • 2
  • X. Xinjilefu
    • 1
  1. 1.Robotics InstituteCarnegie Mellon UniversityPittsburghUSA
  2. 2.Robotics EngineeringWorcester Polytechnic InstituteWorcesterUSA
  3. 3.ConsultantNewbury ParkUSA

Personalised recommendations