Abstract
This article presents a retrospective analysis of Team IHMC’s experience throughout the DARPA Robotics Challenge (DRC), where we took first or second place overall in each of the three phases. As an extremely demanding challenge typical of DARPA, the DRC required rapid research and development to push the boundaries of robotics and set a new benchmark for complex robotic behavior. We present how we addressed each of the eight tasks of the DRC and review our performance in the Finals. While the ambitious competition schedule limited extensive experimentation, we will review the data we collected during the approximately three years of our participation. We discuss some of the significant lessons learned that contributed to our success in the DRC. These include hardware lessons, software lessons, and human-robot integration lessons. We describe refinements to the Coactive Design methodology that helped our designers connect human-machine interaction theory to both implementation and empirical data. This approach helped our team focus our limited resources on the issues most critical to success. In addition to helping readers understand our experiences in developing on a Boston Dynamics Atlas robot for the DRC, we hope this article will provide insights that apply more widely to robotics development and design of human-machine systems.
A version of this article was previously published in the Journal of Field Robotics, vol. 34, issue 2, pp. 241-261, © Wiley 2017.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
https://www.youtube.com/watch?v=27HkxMo6qK0 (accessed 7 SEP 2017).
- 4.
http://robotiq.com/products/industrial-robot-hand (accessed 7 SEP 2017).
- 5.
Some teams combined in later phases making the exact count difficult to assess.
- 6.
On day 1 we fell on the terrain, but were able to recover and complete the task. We pulled the fall and recovery out of the day 1 terrain time for more direct comparison. This extra time is labelled “Fall and Recovery”. Also, the stair task on day 1 was not successful, so it is not an accurate comparison.
- 7.
Dewalt rotary tool used in competition: http://www.dewalt.com/tools/cordless-specialty-cordless-cut-out-tools-dc550ka.aspx (accessed on 7 SEP 2017).
- 8.
A video of a mock final test: https://www.youtube.com/watch?v=EpE6MhaxwOM (accessed on 7 SEP 2017).
- 9.
http://wiki.ros.org/ethzasl_icp_mapping (accessed on 7 SEP 2017).
- 10.
https://www.youtube.com/watch?v=ZG2gGIbtkAk (accessed on 7 SEP 2017).
References
Bradshaw, J. M., Hoffman, R. R., Woods, D. D., & Johnson, M. (2013). The seven deadly myths of “Autonomous Systems”. IEEE Intelligent Systems, 28, 54–61.
DeDonato, M., 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, 275–292.
Fallon, M., et al. (2015). An architecture for online affordance-based perception and whole-body planning. Journal of Field Robotics, 32, 229–254.
Hebert, P., et al. (2015). Mobile manipulation and mobility as manipulation—design and algorithms of RoboSimian. Journal of Field Robotics, 32, 255–274.
Johnson, M., et al. (2014a). Coactive design: Designing support for interdependence in joint activity. Journal of Human-Robot Interaction, 3(1), 2014.
Johnson, M., et al. (2014b). Seven cardinal virtues of human-machine teamwork: examples from the DARPA robotic challenge. IEEE Intelligent Systems, 29, 74–80.
Johnson, M., et al. (2015). Team IHMC’s lessons learned from the DARPA robotics challenge trials. Journal of Field Robotics, 32, 192–208.
Koolen, T., et al. (2012). Capturability-based analysis and control of legged locomotion, Part 1: Theory and application to three simple gait models. The International Journal of Robotics Research, 31, 1094–1113.
Koolen, T. et al., (2013). Summary of Team IHMC’s virtual robotics challenge entry. s.l., s.n. (pp. 307–314).
Pomerleau, F., Colas, F., Siegwart, R., & Magnenat, S. (2013). Comparing ICP variants on real-world data sets. Autonomous Robots, 34, 133–148.
Smith, J., Stephen, D., Lesman, A. & Pratt, J. (2014). Real-time control of humanoid robots using OpenJDK. s.l., s.n. (p. 29).
Stentz, A., et al. (2015). Chimp, the cmu highly intelligent mobile platform. Journal of Field Robotics, 32, 209–228.
Yanco, H. A., et al. (2015). Analysis of human-robot interaction at the darpa robotics challenge trials. Journal of Field Robotics, 32, 420–444.
Acknowledgements
We would like to thank DARPA for sponsoring the Robotics Challenge and encouraging the advancement of robotics capabilities. We would also like to thank DARPA for the funding provided to IHMC to compete in the competition. We also thank Boston Dynamics for providing Atlas, which has been a solid and reliable robotic platform. Lastly, we would like to acknowledge our sponsors Atlassian and Amazon. Atlassian also provided an embedded engineer to ensure our agile practices were effectively applied using their Atlassian software tools.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this chapter
Cite this chapter
Johnson, M. et al. (2018). Team IHMC’s Lessons Learned from the DARPA Robotics Challenge: Finding Data in the Rubble. In: Spenko, M., Buerger, S., Iagnemma, K. (eds) The DARPA Robotics Challenge Finals: Humanoid Robots To The Rescue. Springer Tracts in Advanced Robotics, vol 121. Springer, Cham. https://doi.org/10.1007/978-3-319-74666-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-74666-1_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-74665-4
Online ISBN: 978-3-319-74666-1
eBook Packages: EngineeringEngineering (R0)