Ensemble-CIO: Full-body dynamic motion planning that transfers to physical humanoids
Abstract
While a lot of progress has recently been made in dynamic motion planning for humanoid robots, much of this work has remained limited to simulation. Here we show that executing the resulting trajectories on a Darwin-OP robot, even with local feedback derived from the optimizer, does not result in stable movements. We then develop a new trajectory optimization method, adapting our earlier CIO algorithm to plan through ensembles of perturbed models. This makes the plan robust to model uncertainty, and leads to successful execution on the robot. We obtain a high rate of task completion without trajectory divergence (falling) in dynamic forward walking, sideways walking, and turning, and a similarly high success rate in getting up from the floor (the robot broke before we could quantify the latter). Even though the planning is still done offline, the present work represents a significant step towards automating the tedious scripting of complex movements.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
MuJoCo: A physics engine for model-based control
Todorov, E., Erez, T., & Tassa, Y. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6386109 · Cited by 4,767 · see citing works
Self-citationZERO-MOMENT POINT — THIRTY FIVE YEARS OF ITS LIFE
VUKOBRATOVIC, M. K., & Borovać, B. (2004) · International Journal of Humanoid Robotics · doi:10.1142/s0219843604000083 · Cited by 2,051 · see citing works
Efficient Bipedal Robots Based on Passive-Dynamic Walkers
Collins, S. H., Ruina, A. L., Tedrake, R., & Wisse, M. (2005) · Science · doi:10.1126/science.1107799 · Cited by 1,878 · see citing works
Synthesis and stabilization of complex behaviors through online trajectory optimization
Tassa, Y., Erez, T., & Todorov, E. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386025 · Cited by 774 · see citing works
Self-citationA direct method for trajectory optimization of rigid bodies through contact
Posa, M., Cantu, C., & Tedrake, R. (2014) · The International Journal of Robotics Research · doi:10.1177/0278364913506757 · Cited by 597 · see citing works
Koolen, T., de Boer, T., Rebula, J. R., Goswami, A., & Pratt, J. E. (2012) · The International Journal of Robotics Research · doi:10.1177/0278364912452673 · Cited by 477 · see citing works
Discovery of complex behaviors through contact-invariant optimization
Mordatch, I., Todorov, E. V., & Popović, Z. (2012) · ACM Transactions on Graphics · doi:10.1145/2185520.2185539 · Cited by 451 · see citing works
Self-citationPush Recovery by stepping for humanoid robots with force controlled joints
Stephens, B. J., & Atkeson, C. G. (2010) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/ichr.2010.5686288 · Cited by 210 · see citing works
Byl, K., & Tedrake, R. (2009) · The International Journal of Robotics Research · doi:10.1177/0278364909340446 · Cited by 170 · see citing works
Optimizing walking controllers for uncertain inputs and environments
Wang, J. M., Fleet, D. J., & Hertzmann, A. (2010) · ACM Transactions on Graphics · doi:10.1145/1778765.1778810 · Cited by 113 · see citing works
Variational Policy Search via Trajectory Optimization
Levine, S., & Koltun, V. (2013) · Cited by 84 · see citing works
Animating human lower limbs using contact-invariant optimization
Mordatch, I., Wang, J. M., Todorov, E. V., & Koltun, V. (2013) · ACM Transactions on Graphics · doi:10.1145/2508363.2508365 · Cited by 71 · see citing works
Self-citationNonlinear identification of backlash in robot transmissions
Hovland, G. E., Hanssen, S., Gallestey, E., et al. (2002) · Figshare · Cited by 28 · see citing works
Optimizing walking controllers for uncertain inputs and environments
Wang, J. M., Fleet, D. J., & Hertzmann, A. (2010) · ACM SIGGRAPH Conference Papers (SIGGRAPH) · doi:10.1145/1833349.1778810 · Cited by 18 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Domain randomization for transferring deep neural networks from simulation to the real world
Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., & Abbeel, P. (2017) · 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202133 · Cited by 3,124 · see citing works
“In the context of physics adaptation, Mordatch and collaborators [30] show that training a policy on an ensemble of dynamics models can make the controller robust to modeling error and improve transfer to a real robot.”
BackgroundLearning agile and dynamic motor skills for legged robots
Hwangbo, J., Lee, J., Dosovitskiy, A., Bellicoso, D., Tsounis, V., Koltun, V., & Hutter, M. (2019) · Science Robotics · doi:10.1126/scirobotics.aau5872 · Cited by 1,482 · see citing works
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
Peng, X. B., Andrychowicz, M., Zaremba, W., & Abbeel, P. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8460528 · Cited by 1,309 · see citing works
Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
Rajeswaran, A., Kumar, V., Gupta, A., Vezzani, G., Schulman, J., Todorov, E., & Levine, S. (2018) · Robotics: Science and Systems XIV · doi:10.15607/rss.2018.xiv.049 · Cited by 847 · see citing works
Self-citationSim-to-Real: Learning Agile Locomotion For Quadruped Robots
Tan, J., Zhang, T., Coumans, E., Iscen, A., Bai, Y., Hafner, D., Bohez, S., & Vanhoucke, V. (2018) · Robotics: Science and Systems XIV · doi:10.15607/rss.2018.xiv.010 · Cited by 735 · see citing works
James, S., Wohlhart, P., Kalakrishnan, M., Kalashnikov, D., Irpan, A., Ibarz, J., Levine, S., Hadsell, R., & Bousmalis, K. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01291 · Cited by 420 · see citing works
Preparing for the unknown: Learning a universal policy with online system identification
Yu, W., Tan, J., Karen Liu, C., & Turk, G. (2017) · Robotics: Science and Systems XIII · doi:10.15607/rss.2017.xiii.048 · Cited by 237 · see citing works
Salvato, E., Fenu, G., Medvet, E., & Pellegrino, F. A. (2021) · IEEE Access · doi:10.1109/access.2021.3126658 · Cited by 200 · see citing works
“Domain randomisation (DR) has already achieved good results in sim-to-real transfer of robotics controllers outside RL [54, 75, 76, 77, 78, 79].”
BackgroundADAPT: Zero-Shot Adaptive Policy Transfer for Stochastic Dynamical Systems
Harrison, J., Garg, A., Ivanovic, B., Zhu, Y., Savarese, S., Fei-Fei, L., & Pavone, M. (2017) · arXiv · doi:10.48550/arxiv.1707.04674 · Cited by 21
- Authors
- Mordatch, I., Lowrey, K., & Todorov, E.
- Affiliations
- University of Washington (US)
- Venue
- 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- Publisher
- IEEE
- Published
- 2015-09
- Pages
- 5307-5314
- ISSN
- 2153-0858 (ISSN-L)
- OpenAlex
- W2205975260
- Cited by
- 135
- References
- 14
- Citations by year
- 2026: 2 · 2025: 9 · 2024: 8 · 2023: 7 · 2022: 11 · 2021: 13 · 2020: 17 · 2019: 30 · 2018: 17 · 2017: 14 · 2016: 6 · 2015: 1
- FWCI
- 24.35
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publishedVersion)
- Funders
- National Science Foundation
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Robotic Locomotion and Control
- Physical Sciences › Engineering › Control and Systems Engineering › Human Motion and Animation
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotic Path Planning Algorithms
- Keywords
- dynamic motion planning, humanoid robots, trajectory optimization, model uncertainty, robustness, whole-body movement, walking, offline planning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
