Achieving Reliable Humanoid Robot Operations in the DARPA Robotics Challenge: Team WPI-CMU’s Approach
The DARPA Robotics Challenge (DRC) required participating human-robot teams to integrate mobility, manipulation, perception and operator interfaces to complete a simulated disaster mission. We describe our approach to the development of manipulation and locomotion capabilities for the humanoid robot atlas unplugged developed by Boston Dynamics. We focus on our approach, results and lessons learned from the DRC Finals to demonstrate our strategy including extensive operator practice, explicit monitoring for robot errors, adding additional sensing, and enabling the operator to control and monitor the robot at varying degrees of abstraction. Our safety-first strategy worked: we avoided falling and remote operators could safely recover from difficult situations. We were the only team in the DRC Finals that attempted all tasks, scored points (14/16), did not require physical human intervention (a reset), and did not fall in the two missions during the two days of tests. We also had the most consistent pair of runs. We ranked 3rd out of 23 teams when the scores from two official runs were averaged.
This material is based upon work supported in part by the DARPA Robotics Challenge program under DRC Contract No. HR0011-14-C-0011.
- Atkeson, C. G. (2015). Big Hero 6: Let’s Build Baymax. http://www.build-baymax.org.
- Bai, X., & Sapiro, G. (2007, October). A geodesic framework for fast interactive image and video segmentation and matting. In IEEE 11th International Conference on Computer Vision, 2007. ICCV 2007 (pp. 1–8).Google Scholar
- Banerjee, N., Long, X., Du, R., Polido, F., Feng, S., Atkeson, C. G., et al. (2015a, November). Human-supervised control of the atlas humanoid robot for traversing doors. In 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) (pp. 722–729).Google Scholar
- Banerjee, N., Long, X., Du, R., Polido, F., Feng, S., Atkeson, C. G., et al. (2015b). Human-supervised control of the ATLAS humanoid robot for traversing doors. In 15th IEEE-RAS International Conference on Humanoid Robots (Humanoids).Google Scholar
- Berenson, D. (2011, May). Constrained manipulation planning. Ph.D. thesis. Pittsburgh, PA: Robotics Institute, Carnegie Mellon University.Google Scholar
- Feng, S., Xinjilefu, X., Atkeson, C. G., & Kim, J. (2015b). Optimization based controller design and implementation for the Atlas robot in the DARPA Robotics Challenge Finals. In 15th IEEE-RAS International Conference on Humanoid Robots (Humanoids).Google Scholar
- Geiger, A. (2012). LIBVISO2: C++ Library for Visual Odometry 2. www.cvlibs.net/software/libviso/.
- Huang, W., Kim, J., & Atkeson, C. (2013, May). Energy-based optimal step planning for humanoids. In 2013 International Conference on Robotics and Automation (ICRA) (pp. 3124–3129). Germany: Karlsruhe.Google Scholar
- IHMC. (2015). Personal communication.Google Scholar
- Kalakrishnan, M., Chitta, S., Theodorou, E., Pastor, P., & Schaal, S. (2011, May). Stomp: Stochastic trajectory optimization for motion planning. In 2011 IEEE International Conference on Robotics and Automation (ICRA) (pp. 4569–4574).Google Scholar
- Knoedler, K., Dimitrov, V., Conn, D., Gennert, M. A., & Padir, T. (2015). Towards supervisory control of humanoid robots for driving vehicles during disaster response missions. In IEEE International Conference on Technologies for Practical Robot Applications.Google Scholar
- Kuffner, J., & LaValle, S. (2000). RRT-connect: An efficient approach to single-query path planning. In IEEE International Conference on Robotics and Automation, 2000. Proceedings. ICRA ’00 (Vol. 2, pp. 995–1001).Google Scholar
- LaValle, S. M. (2006). Planning Algorithms. Cambridge University Press, Cambridge, U.K. http://planning.cs.uiuc.edu/.
- Liu, C., Atkeson, C. G., Feng, S., & Xinjilefu, X. (2015). Full-body motion planning and control for the car egress task of the DARPA Robotics Challenge. In 15th IEEE-RAS International Conference on Humanoid Robots (Humanoids).Google Scholar
- Mamou, K., & Ghorbel, F. (2009, November). A simple and efficient approach for 3D mesh approximate convex decomposition. In 2009 16th IEEE International Conference on Image Processing (ICIP) (pp. 3501–3504).Google Scholar
- Matsuo, T., Fukushima, N., & Ishibashi, Y. (2013). Weighted joint bilateral filter with slope depth compensation filter for depth map refinement. VISAPP, 2, 300–309.Google Scholar
- MIT. (2015a). Personal communication.Google Scholar
- MIT. (2015b). Egress robustness tests. https://www.youtube.com/watch?v=F5CBRmDQXTk.
- Pratt, J., Carff, J., Drakunov, S., & Goswami, A. (2006, December). Capture point: A step toward humanoid push recovery. 6th IEEE-RAS International Conference on Humanoid Robots (Humanoids) (pp. 200–207). Italy: Genoa.Google Scholar
- Ratliff, N., Zucker, M., Bagnell, J., & Srinivasa, S. (2009, May). Chomp: Gradient optimization techniques for efficient motion planning. In IEEE International Conference on Robotics and Automation, 2009. ICRA ’09 (pp. 489–494).Google Scholar
- Schulman, J., Duan, Y., Ho, J., Lee, A., Awwal, I., Bradlow, H., et al. (2014). Motion planning with sequential convex optimization and convex collision checking. The International Journal of Robotics Research.Google Scholar
- 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
- Xinjilefu, X., Feng, S., & Atkeson, C. (2015). Center of mass estimator for humanoids and its application in modelling error compensation, fall detection and prevention. In 15th IEEE-RAS International Conference on Humanoid Robots (Humanoids).Google Scholar
- Xinjilefu, X., Feng, S., Huang, W., & Atkeson, C. G. (2014). Decoupled state estimation for humanoids using full-body dynamics. In IEEE International Conference on Robotics and Automation (ICRA) (pp. 195–201). IEEE.Google Scholar