{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T15:35:58Z","timestamp":1787758558146,"version":"build-2784847793"},"reference-count":38,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"86","content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2024,1,17]]},"abstract":"<jats:p>Legged locomotion is a complex control problem that requires both accuracy and robustness to cope with real-world challenges. Legged systems have traditionally been controlled using trajectory optimization with inverse dynamics. Such hierarchical model-based methods are appealing because of intuitive cost function tuning, accurate planning, generalization, and, most importantly, the insightful understanding gained from more than one decade of extensive research. However, model mismatch and violation of assumptions are common sources of faulty operation. Simulation-based reinforcement learning, on the other hand, results in locomotion policies with unprecedented robustness and recovery skills. Yet, all learning algorithms struggle with sparse rewards emerging from environments where valid footholds are rare, such as gaps or stepping stones. In this work, we propose a hybrid control architecture that combines the advantages of both worlds to simultaneously achieve greater robustness, foot-placement accuracy, and terrain generalization. Our approach uses a model-based planner to roll out a reference motion during training. A deep neural network policy is trained in simulation, aiming to track the optimized footholds. We evaluated the accuracy of our locomotion pipeline on sparse terrains, where pure data-driven methods are prone to fail. Furthermore, we demonstrate superior robustness in the presence of slippery or deformable ground when compared with model-based counterparts. Last, we show that our proposed tracking controller generalizes across different trajectory optimization methods not seen during training. In conclusion, our work unites the predictive capabilities and optimality guarantees of online planning with the inherent robustness attributed to offline learning.<\/jats:p>","DOI":"10.1126\/scirobotics.adh5401","type":"journal-article","created":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T13:58:17Z","timestamp":1705499897000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":117,"title":["DTC: Deep Tracking Control"],"prefix":"10.1126","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1851-2875","authenticated-orcid":true,"given":"Fabian","family":"Jenelten","sequence":"first","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, 8092 Zurich, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5928-1237","authenticated-orcid":true,"given":"Junzhe","family":"He","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, 8092 Zurich, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farbod","family":"Farshidian","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, 8092 Zurich, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-4990","authenticated-orcid":true,"given":"Marco","family":"Hutter","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, 8092 Zurich, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"J. Z. Kolter M. P. Rodgers A. Y. Ng A control architecture for quadruped locomotion over rough terrain in 2008 IEEE International Conference on Robotics and Automation (IEEE 2008) pp. 811\u2013818.","DOI":"10.1109\/ROBOT.2008.4543305"},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","unstructured":"M. Kalakrishnan J. Buchli P. Pastor M. Mistry S. Schaal Fast robust quadruped locomotion over challenging terrain in 2010 IEEE International Conference on Robotics and Automation (IEEE 2010) pp. 2665\u20132670.","DOI":"10.1109\/ROBOT.2010.5509805"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2798285"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3003464"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3007427"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"P. Fankhauser M. Bjelonic C. Dario Bellicoso T. Miki M. Hutter Robust rough-terrain locomotion with a quadrupedal robot in 2018 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2018) pp. 5761\u20135768.","DOI":"10.1109\/ICRA.2018.8460731"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3275384"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"C. Mastalli W. Merkt G. Xin J. Shim M. Mistry I. Havoutis S. Vijayakumar Agile maneuvers in legged robots: a predictive control approach arXiv:2203.07554v2 [cs.RO] (2022).","DOI":"10.21203\/rs.3.rs-1870369\/v1"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2794620"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"e_1_3_2_12_2","unstructured":"N. Rudin D. Hoeller P. Reist M. Hutter Learning to walk in minutes using massively parallel deep reinforcement learning in 5th Annual Conference on Robot Learning (MLRPress 2021) pp. 91\u2013100."},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"e_1_3_2_15_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) (IEEE 2022) pp. 2497\u20132503.","DOI":"10.1109\/IROS47612.2022.9981198"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14115"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","unstructured":"H. Duan A. Malik J. Dao A. Saxena K. Green J. Siekmann A. Fern J. Hurst Sim-to-real learning of footstep-constrained bipedal dynamic walking in 2022 International Conference on Robotics and Automation (ICRA) (IEEE 2022) pp. 10428\u201310434.","DOI":"10.1109\/ICRA46639.2022.9812015"},{"key":"e_1_3_2_18_2","unstructured":"W. Yu D. Jain A. Escontrela A. Iscen P. Xu E. Coumans S. Ha J. Tan T. Zhang Visual-locomotion: Learning to walk on complex terrains with vision in Proceedings of the 5th Conference on Robot Learning A. Faust D. Hsu G. Neumann Eds. (MLResearchPress 2022) pp. 1291\u20131302."},{"key":"e_1_3_2_19_2","unstructured":"A. Agarwal A. Kumar J. Malik D. Pathak Legged locomotion in challenging terrains using egocentric vision in 6th Annual Conference on Robot Learning (MLResearchPress 2022) pp. 403\u2013415."},{"key":"e_1_3_2_20_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] (24 May 2023)."},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"R. J. Griffin G. Wiedebach S. McCrory S. Bertrand I. Lee J. Pratt Footstep planning for autonomous walking over rough terrain in 2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids) (IEEE 2019) pp. 9\u201316.","DOI":"10.1109\/Humanoids43949.2019.9035046"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"F. Jenelten R. Grandia F. Farshidian M. Hutter Tamols: Terrain-aware motion optimization for legged systems IEEE Transactions on Robotics (IEEE 2022) pp.3395\u20133413.","DOI":"10.1109\/TRO.2022.3186804"},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","unstructured":"P. Brakel S. Bohez L. Hasenclever N. Heess K. Bousmalis Learning coordinated terrain-adaptive locomotion by imitating a centroidal dynamics planner in 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2022) pp. 10 335\u201310 342.","DOI":"10.1109\/IROS47612.2022.9981648"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.854212"},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201311","article-title":"DeepMimic","volume":"37","author":"Peng X. B.","year":"2018","unstructured":"X. B. Peng, P. Abbeel, S. Levine, M. van de Panne, DeepMimic: Example-guided deep reinforcement learning of physics-based character skills. ACM Transactions on Graphics 37, 1\u201314 (2018).","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"e_1_3_2_27_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] (31 March 2022)."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2979660"},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"X. B. Peng G. Berseth K. Yin M. van de Panne Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning (ACM Transactions on Graphics Proc. SIGGRAPH 2017) (2017) vol. 36.","DOI":"10.1145\/3072959.3073602"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"O. Melon M. Geisert D. Surovik I. Havoutis M. Fallon Reliable trajectories for dynamic quadrupeds using analytical costs and learned initializations in 2020 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2020) pp. 1410\u20131416.","DOI":"10.1109\/ICRA40945.2020.9196562"},{"key":"e_1_3_2_31_2","unstructured":"D. Surovik O. Melon M. Geisert M. Fallon I. Havoutis Learning an expert skill-space for replanning dynamic quadruped locomotion over obstacles in Proceedings of the 2020 Conference on Robot Learning J. Kober F. Ramos C. Tomlin eds. (MLResearchPress 2021) pp. 1509\u20131518."},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"O. Melon R. Orsolino D. Surovik M. Geisert I. Havoutis M. Fallon Receding-horizon perceptive trajectory optimization for dynamic legged locomotion with learned initialization in 2021 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2021) pp. 9805\u20139811 .","DOI":"10.1109\/ICRA48506.2021.9560794"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3172469"},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Z. Xie X. Da B. Babich A. Garg M. V. de Panne Glide: Generalizable quadrupedal locomotion in diverse environments with a centroidal model in Algorithmic Foundations of Robotics XV S. M. LaValle J. M. O\u2019Kane M. Otte D. Sadigh P. Tokekar Eds. (Springer International Publishing 2023) pp. 523\u2013539.","DOI":"10.1007\/978-3-031-21090-7_31"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"M. Hutter C. Gehring D. Jud A. Lauber C. D. Bellicoso V. Tsounis J. Hwangbo K. Bodie P. Fankhauser M. Bloesch R. Diethelm S. Bachmann A. Melzer M. Hoepflinger Hutter2016 - a highly mobile and dynamic quadrupedal robot in 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2016) pp. 38\u201344.","DOI":"10.1109\/IROS.2016.7758092"},{"key":"e_1_3_2_36_2","unstructured":"W. Jakob J. Rhinelander D. Moldovan pybind11\u2013seamless operability between c++11 and python (2017); https:\/\/github.com\/pybind\/pybind11."},{"key":"e_1_3_2_37_2","unstructured":"J. Schulman F. Wolski P. Dhariwal A. Radford O. Klimov Proximal policy optimization algorithms arXiv:1707.06347 [cs.LG] (28 August 2017)."},{"key":"e_1_3_2_38_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_39_2","unstructured":"F. Jenelten J. He F. Farshidian M. Hutter Evaluation of tracking performance and robustness for a hybrid locomotion controller (Zenodo 2023); https:\/\/doi.org\/10.5061\/dryad.b5mkkwhkq."}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.adh5401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T13:58:41Z","timestamp":1705499921000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.adh5401"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,17]]},"references-count":38,"journal-issue":{"issue":"86","published-print":{"date-parts":[[2024,1,17]]}},"alternative-id":["10.1126\/scirobotics.adh5401"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.adh5401","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,17]]},"assertion":[{"value":"2023-04-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-19","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eadh5401"}}