{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T20:45:37Z","timestamp":1776199537915,"version":"3.50.1"},"reference-count":43,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"88","content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2024,3,13]]},"abstract":"<jats:p>Performing agile navigation with four-legged robots is a challenging task because of the highly dynamic motions, contacts with various parts of the robot, and the limited field of view of the perception sensors. Here, we propose a fully learned approach to training such robots and conquer scenarios that are reminiscent of parkour challenges. The method involves training advanced locomotion skills for several types of obstacles, such as walking, jumping, climbing, and crouching, and then using a high-level policy to select and control those skills across the terrain. Thanks to our hierarchical formulation, the navigation policy is aware of the capabilities of each skill, and it will adapt its behavior depending on the scenario at hand. In addition, a perception module was trained to reconstruct obstacles from highly occluded and noisy sensory data and endows the pipeline with scene understanding. Compared with previous attempts, our method can plan a path for challenging scenarios without expert demonstration, offline computation, a priori knowledge of the environment, or taking contacts explicitly into account. Although these modules were trained from simulated data only, our real-world experiments demonstrate successful transfer on hardware, where the robot navigated and crossed consecutive challenging obstacles with speeds of up to 2 meters per second.<\/jats:p>","DOI":"10.1126\/scirobotics.adi7566","type":"journal-article","created":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T17:58:57Z","timestamp":1710352737000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":211,"title":["ANYmal parkour: Learning agile navigation for quadrupedal robots"],"prefix":"10.1126","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8010-9011","authenticated-orcid":true,"given":"David","family":"Hoeller","sequence":"first","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, Zurich, Switzerland."},{"name":"NVIDIA, Zurich, Switzerland."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5893-0348","authenticated-orcid":true,"given":"Nikita","family":"Rudin","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, Zurich, Switzerland."},{"name":"NVIDIA, Zurich, Switzerland."}]},{"given":"Dhionis","family":"Sako","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, Zurich, Switzerland."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-4990","authenticated-orcid":true,"given":"Marco","family":"Hutter","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, Zurich, Switzerland."}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"R. Grandia F. Jenelten S. Yang F. Farshidian M. Hutter Perceptive locomotion through nonlinear model predictive control. arXiv:2208.08373 [quant-ph] (2022).","DOI":"10.1109\/TRO.2023.3275384"},{"key":"e_1_3_2_3_2","first-page":"3395","article-title":"TAMOLS: Terrain-aware motion optimization for legged systems","volume":"38","author":"Jenelten F.","year":"2022","unstructured":"F. Jenelten, R. Grandia, F. Farshidian, M. Hutter, TAMOLS: Terrain-aware motion optimization for legged systems. T-RO 38, 3395\u20133413 (2022).","journal-title":"T-RO"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"D. Kim D. Carballo J. Di Carlo B. Katz G. Bledt B. Lim S. Kim Vision aided dynamic exploration of unstructured terrain with a small-scale quadruped robot in 2020 IEEE International Conference on Robotics and Automation (ICRA) Paris France August 2020 (IEEE 2020) pp. 2464\u20132470.","DOI":"10.1109\/ICRA40945.2020.9196777"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"e_1_3_2_6_2","doi-asserted-by":"crossref","unstructured":"A. Loquercio A. Kumar J. Malik Learning visual locomotion with cross-modal supervision In 2023 International Conference on Robotics and Automation (ICRA) (IEEE 2023) pp. 7295\u20137302.","DOI":"10.1109\/ICRA48891.2023.10160760"},{"key":"e_1_3_2_7_2","first-page":"2908","article-title":"Rloc: Terrain-aware legged locomotion using reinforcement learning and optimal control","volume":"38","author":"Gangapurwala S.","year":"2022","unstructured":"S. Gangapurwala, M. Geisert, R. Orsolino, M. Fallon, I. Havoutis, Rloc: Terrain-aware legged locomotion using reinforcement learning and optimal control. T-RO 38, 2908\u20132927 (2022).","journal-title":"T-RO"},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"M. H. Raibert Legged Robots That Balance (MIT Press 1986) pp. 1\u201389.","DOI":"10.1109\/MEX.1986.4307016"},{"key":"e_1_3_2_9_2","unstructured":"D. Kim J. D. Carlo B. Katz G. Bledt S. Kim Highly dynamic quadruped locomotion via whole-body impulse control and model predictive control. arXiv:1909.06586 (2019)."},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Q. Nguyen M. J. Powell B. Katz J. D. Carlo S. Kim Optimized jumping on the MIT Cheetah 3 robot in 2019 International Conference on Robotics and Automation (ICRA) Montreal QC Canada May 2019 (IEEE 2019) pp. 7448\u20137454.","DOI":"10.1109\/ICRA.2019.8794449"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103703"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"N. Rudin D. Hoeller M. Bjelonic M. Hutter Advanced skills by learning locomotion and local navigation end-to-end in 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) Kyoto Japan October 2022 (IEEE 2022) pp. 2497\u20132503.","DOI":"10.1109\/IROS47612.2022.9981198"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3084374"},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"S. H. Jeon S. Kim D. Kim Real-time optimal landing control of the MIT Mini Cheetah. arXiv:2110.02799 [cs.RO] (2021).","DOI":"10.1109\/ICRA46639.2022.9811796"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Y. Ma F. Farshidian M. Hutter Learning arm-assisted fall damage reduction and recovery for legged mobile manipulators. arXiv:2303.05486 [cs.RO] (2023).","DOI":"10.1109\/ICRA48891.2023.10160582"},{"key":"e_1_3_2_17_2","unstructured":"S. Bohez S. Tunyasuvunakool P. Brakel F. Sadeghi L. Hasenclever Y. Tassa E. Parisotto J. Humplik T. Haarnoja R. Hafner M. Wulfmeier M. Neunert B. Moran N. Siegel A. Huber F. Romano N. Batchelor F. Casarini J. Merel R. Hadsell N. Heess Imitate and repurpose: Learning reusable robot movement skills from human and animal behaviors. arXiv:2203.17138 [cs.RO] (2022)."},{"key":"e_1_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Y. Ji G. B. Margolis P. Agrawal Dribblebot: Dynamic legged manipulation in the wild in 2023 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2023) pp. 5155\u20135162.","DOI":"10.1109\/ICRA48891.2023.10160325"},{"key":"e_1_3_2_19_2","doi-asserted-by":"crossref","unstructured":"J. Siekmann K. Green J. Warila A. Fern J. Hurst Blind bipedal stair traversal via sim-to-real reinforcement learning in Proceedings of Robotics: Science and Systems XVII D. A. Shell M. Toussaint M. A. Hsieh Eds. (RSS 2021); www.roboticsproceedings.org\/rss17\/p061.html.","DOI":"10.15607\/RSS.2021.XVII.061"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Z. Li X. B. Peng P. Abbeel S. Levine G. Berseth K. Sreenath Robust and versatile bipedal jumping control through multi-task reinforcement learning. arXiv:2302.09450 [cs.RO] (2023).","DOI":"10.15607\/RSS.2023.XIX.052"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"e_1_3_2_22_2","first-page":"586","article-title":"An efficient acyclic contact planner for multiped robots","volume":"34","author":"Tonneau S.","year":"2018","unstructured":"S. Tonneau, A. Del Prete, J. Pettr\u00e9, C. Park, D. Manocha, N. Mansard, An efficient acyclic contact planner for multiped robots. T-RO 34, 586\u2013601 (2018).","journal-title":"T-RO"},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","unstructured":"L. Wellhausen M. Hutter Rough terrain navigation for legged robots using reachability planning and template learning in 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) Prague Czech Republic October 2021 (IEEE 2021) pp.6914\u20136921.","DOI":"10.1109\/IROS51168.2021.9636358"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"M. Pfeiffer M. Schaeuble J. Nieto R. Siegwart C. Cadena From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots in IEEE International Conference on Robotics and Automation (ICRA) Singapore June 2017 (IEEE 2017) pp. 1527\u20131533.","DOI":"10.1109\/ICRA.2017.7989182"},{"key":"e_1_3_2_25_2","unstructured":"E. Kaufmann A. Loquercio R. Ranftl A. Dosovitskiy V. Koltun D. Scaramuzza Deep drone racing: Learning agile flight in dynamic environments in Proceedings of the 2nd Conference on Robot Learning (PMLR) A. Billard A. Dragan J. Peters J. Morimoto Eds. (MLResearchPress 2018) pp. 133\u2013145."},{"key":"e_1_3_2_26_2","doi-asserted-by":"crossref","unstructured":"F. Sadeghi S. Levine CAD2RL: Real single-image flight without a single real image in Proceedings of Robotics: Science and Systems XIII N. Amato S. Srinivasa N. Ayanian S. Kuindersma Eds. (RSS 2017); www.roboticsproceedings.org\/rss13\/p34.html.","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"F. Sadeghi DIVIS: Domain invariant visual servoing for collision-free goal reaching in Proceedings of Robotics: Science and Systems XV A. Bicchi H. Kress-Gazit S. Hutchinson Eds. (RSS 2019); www.roboticsproceedings.org\/rss15\/p55.html.","DOI":"10.15607\/RSS.2019.XV.055"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068639"},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"G. Kahn P. Abbeel S. Levine BADGR: An autonomous self-supervised learning-based navigation system. arXiv:2002.05700 (2020).","DOI":"10.1109\/LRA.2021.3057023"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"B. Yang L. Wellhausen T. Miki M. Liu M. Hutter Real-time optimal navigation planning using learned motion costs in 2021 IEEE International Conference on Robotics and Automation (ICRA) Xi'an China June 2021 (IEEE 2021) pp. 9283\u20139289.","DOI":"10.1109\/ICRA48506.2021.9561861"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530110"},{"key":"e_1_3_2_32_2","unstructured":"J. Merel A. Ahuja V. Pham S. Tunyasuvunakool S. Liu D. Tirumala N. Heess G. Wayne Hierarchical visuomotor control of humanoids paper presented at ICLR 2019: The Seventh International Conference on Learning Representations New Orleans USA 6 to 9 May 2019."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb2174"},{"key":"e_1_3_2_34_2","unstructured":"K. Caluwaerts A. Iscen J. C. Kew W. Yu T. Zhang D. Freeman K.-H. Lee L. Lee S. Saliceti V. Zhuang N. Batchelor S. Bohez F. Casarini J. E. Chen O. Cortes E. Coumans A. Dostmohamed G. Dulac-Arnold A. Escontrela E. Frey R. Hafner D. Jain B. Jyenis Y. Kuang E. Lee L. Luu O. Nachum K. Oslund J. Powell D. Reyes F. Romano F. Sadeghi R. Sloat B. Tabanpour D. Zheng M. Neunert R. Hadsell N. Heess F. Nori J. Seto C. Parada V. Sindhwani V. Vanhoucke J. Tan Barkour: Benchmarking animal-level agility with quadruped robots. arXiv:2305.14654 [cs.RO] (2023)."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2801794"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"H. Oleynikova Z. Taylor M. Fehr R. Siegwart J. Nieto Voxblox: Incremental 3D Euclidean signed distance fields for on-board MAV planning in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) Vancouver BC Canada September 2017 (IEEE 2017) pp. 1366\u20131373.","DOI":"10.1109\/IROS.2017.8202315"},{"key":"e_1_3_2_37_2","unstructured":"A. Agarwal A. Kumar J. Malik D. Pathak Legged locomotion in challenging terrains using egocentric vision in Proceedings of the 6th Annual Conference on Robot Learning (PMLR) K. Liu D. Kulic J. Ichnowski Eds. (MLResearchPress 2022) pp. 403\u2013415."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184779"},{"key":"e_1_3_2_39_2","unstructured":"N. Rudin D. Hoeller P. Reist M. Hutter Learning to walk in minutes using massively parallel deep reinforcement learning in Proceedings of the 5th Conference on Robot Learning (PMLR) A. Faust D. Hsu G. Neumann Eds. (MLResearch Press 2022) pp. 91\u2013100."},{"key":"e_1_3_2_40_2","doi-asserted-by":"crossref","unstructured":"T. Miki L. Wellhausen R. Grandia F. Jenelten T. Homberger M. Hutter Elevation mapping for locomotion and navigation using GPU in 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2022) pp. 2273\u20132280.","DOI":"10.1109\/IROS47612.2022.9981507"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2849506"},{"key":"e_1_3_2_42_2","unstructured":"M. Macklin Warp: A High-Performance Python Framework for GPU Simulation and Graphics (NVIDIA GPU Technology Conference 2022); www.nvidia.com\/en-us\/on-demand\/session\/gtcspring22-s41599\/."},{"key":"e_1_3_2_43_2","unstructured":"V. Makoviychuk L. Wawrzyniak Y. Guo M. Lu K. Storey M. Macklin D. Hoeller N. Rudin A. Allshire A. Handa G. State Isaac gym: High performance GPU based physics simulation for robot learning in Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1 (Round 2) J. Vanschoren S. Yeung Eds. (NeurIPS 2021)."},{"key":"e_1_3_2_44_2","doi-asserted-by":"crossref","unstructured":"F. Abdolhosseini H. Y. Ling Z. Xie X. B. Peng M. Van de Panne On learning symmetric locomotion in Proceedings of the 12th ACM SIGGRAPH Conference on Motion Interaction and Games (ACM 2019) pp. 1\u201310.","DOI":"10.1145\/3359566.3360070"}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.adi7566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T17:59:50Z","timestamp":1710352790000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.adi7566"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,13]]},"references-count":43,"journal-issue":{"issue":"88","published-print":{"date-parts":[[2024,3,13]]}},"alternative-id":["10.1126\/scirobotics.adi7566"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.adi7566","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,13]]},"assertion":[{"value":"2023-05-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-16","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eadi7566"}}