{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T23:57:55Z","timestamp":1776211075881,"version":"3.50.1"},"reference-count":61,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"26","funder":[{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"publisher","award":["200021-166232"],"award-info":[{"award-number":["200021-166232"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Intel Network on Intelligent Systems"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2019,1,30]]},"abstract":"<jats:p>A method for learning agile control policies uses simulated data to enable precise, efficient movements in a complex physical robot.<\/jats:p>","DOI":"10.1126\/scirobotics.aau5872","type":"journal-article","created":{"date-parts":[[2019,1,17]],"date-time":"2019-01-17T00:16:12Z","timestamp":1547684172000},"source":"Crossref","is-referenced-by-count":1145,"title":["Learning agile and dynamic motor skills for legged robots"],"prefix":"10.1126","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3444-8079","authenticated-orcid":true,"given":"Jemin","family":"Hwangbo","sequence":"first","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, Zurich, Switzerland."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5072-7385","authenticated-orcid":true,"given":"Joonho","family":"Lee","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, Zurich, Switzerland."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1851-0976","authenticated-orcid":true,"given":"Alexey","family":"Dosovitskiy","sequence":"additional","affiliation":[{"name":"Intelligent Systems Lab, Intel, Munich, Germany."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3856-0735","authenticated-orcid":true,"given":"Dario","family":"Bellicoso","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, Zurich, Switzerland."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3428-8455","authenticated-orcid":true,"given":"Vassilios","family":"Tsounis","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, Zurich, Switzerland."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0858-0970","authenticated-orcid":true,"given":"Vladlen","family":"Koltun","sequence":"additional","affiliation":[{"name":"Intelligent Systems Lab, Intel, Santa Clara, CA, USA."}]},{"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":"publisher","DOI":"10.3182\/20080706-5-KR-1001.01833"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.7210\/jrsj.30.372"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"S. Seok A. Wang M. Y. Chuah D. Otten J. Lang S. Kim Design principles for highly efficient quadrupeds and implementation on the MIT Cheetah robot in 2013 IEEE International Conference on Robotics and Automation (IEEE 2013) pp. 3307\u20133312.","DOI":"10.1109\/ICRA.2013.6631038"},{"key":"e_1_3_2_5_2","unstructured":"Spotmini autonomous navigation https:\/\/youtu.be\/Ve9kWX_KXus. [accessed 11 August 2018]."},{"key":"e_1_3_2_6_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 ANYmal - a highly mobile and dynamic quadrupedal robot in 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_7_2","doi-asserted-by":"publisher","DOI":"10.1242\/jeb.202.23.3325"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1115\/1.3139652"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"J. Pratt J. Carff S. Drakunov A. Goswami Capture point: A step toward humanoid push recovery in 2006 6th IEEE-RAS International Conference on Humanoid Robots (IEEE 2006) pp. 200\u2013207.","DOI":"10.1109\/ICHR.2006.321385"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008844026298"},{"key":"e_1_3_2_11_2","unstructured":"W. J. Schwind Spring loaded inverted pendulum running: A plant model thesis University of Michigan (1998)."},{"key":"e_1_3_2_12_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_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2794620"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2665685"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185539"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"F. Farshidian M. Neunert A. W. Winkler G. Rey J. Buchli An efficient optimal planning and control framework for quadrupedal locomotion in 2017 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2017) pp. 93\u2013100.","DOI":"10.1109\/ICRA.2017.7989016"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913506757"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852785"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"e_1_3_2_20_2","unstructured":"R. Tedrake T. W. Zhang H. S. Seung Stochastic policy gradient reinforcement learning on a simple 3d biped in 2004 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2004) pp. 2849\u20132854."},{"key":"e_1_3_2_21_2","unstructured":"J. Yosinski J. Clune D. Hidalgo S. Nguyen J. C. Zagal H. Lipson Evolving robot gaits in hardware: The hyperNEAT generative encoding vs. parameter optimization in Proceedings of the 20th European Conference on Artificial Life (Springer MIT Press 2011) pp. 890\u2013897."},{"key":"e_1_3_2_22_2","unstructured":"S. Levine V. Koltun Learning complex neural network policies with trajectory optimization in Proceedings of the 31st International Conference on Machine Learning PMLR (PMLR 2014) pp. 829\u2013837."},{"key":"e_1_3_2_23_2","unstructured":"J. Schulman S. Levine P. Abbeel M. Jordan P. Moritz Trust region policy optimization in International Conference on Machine Learning (ICML Omnipress 2015) pp. 1889\u20131897."},{"key":"e_1_3_2_24_2","unstructured":"J. Schulman F. Wolski P. Dhariwal A. Radford O. Klimov Proximal policy optimization algorithms arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_25_2","unstructured":"N. Heess S. Sriram J. Lemmon J. Merel G. Wayne Y. Tassa T. Erez Z. Wang A. Eslami M. Riedmiller D. Silver Emergence of locomotion behaviours in rich environments arXiv:1707.02286 (2017)."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Z. Xie G. Berseth P. Clary J. Hurst M. van de Panne Feedback control for Cassie with deep reinforcement learning arXiv:1803.05580 (2018).","DOI":"10.1109\/IROS.2018.8593722"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2799426"},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"M. Neunert T. Boaventura J. Buchli Why Off-The-Shelf Physics Simulators Fail in Evaluating Feedback Controller Performance-A Case Study for Quadrupedal Robots. Advances in Cooperative Robotics (World Scientific 2017) pp. 464\u2013472.","DOI":"10.1142\/9789813149137_0055"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1133687"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1163\/016918609X12529286896877"},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"D. Nguyen-Tuong J. Peters Learning robot dynamics for computed torque control using local gaussian processes regression in 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems (LAB-RS) (IEEE 2008) pp. 59\u201364.","DOI":"10.1109\/LAB-RS.2008.16"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-9399(1996)122:10(966)"},{"key":"e_1_3_2_34_2","unstructured":"R. S. Sutton A. G. Barto Reinforcement Learning: An Introduction (MIT Press 1998) vol. 1."},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"I. Mordatch K. Lowrey E. Todorov Ensemble-cio: Full-body dynamic motion planning that transfers to physical humanoids in 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2015) pp. 5307\u20135314.","DOI":"10.1109\/IROS.2015.7354126"},{"key":"e_1_3_2_36_2","article-title":"Sim-to-real: Learning agile locomotion for quadruped robots","author":"Tan J.","year":"2018","unstructured":"J. Tan, T. Zhang, E. Coumans, A. Iscen, Y. Bai, D. Hafner, S. Bohez, V. Vanhoucke, Sim-to-real: Learning agile locomotion for quadruped robots. Proc. Robot. 10.15607\/RSS.2018.XIV.010 (2018).","journal-title":"Proc. Robot."},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","unstructured":"X. B. Peng M. Andrychowicz W. Zaremba P. Abbeel Sim-to-real transfer of robotic control with dynamics randomization. arXiv:1710.06537 (2017).","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"e_1_3_2_38_2","doi-asserted-by":"crossref","unstructured":"N. Jakobi P. Husbands I. Harvey Noise and The Reality Gap: The Use of Simulation in Evolutionary Robotics European Conference on Artificial Life (Springer 1995) pp. 704\u2013720.","DOI":"10.1007\/3-540-59496-5_337"},{"key":"e_1_3_2_39_2","unstructured":"A. Dosovitskiy V. Koltun Learning to act by predicting the future in International Conference on Learning Representations (ICLR) (PMLR 2017)."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2015.2505910"},{"key":"e_1_3_2_41_2","unstructured":"R. Featherstone Rigid Body Dynamics Algorithms (Springer 2014)."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2792536"},{"key":"e_1_3_2_43_2","unstructured":"R. Smith Open dynamics engine (2005)."},{"key":"e_1_3_2_44_2","unstructured":"D. A. Winter The Biomechanics and Motor Control of Human Gait: Normal Elderly and Pathological (University of Waterloo Press ed. 2 1991)."},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"H.-W. Park S. Park S. Kim Variable-speed quadrupedal bounding using impulse planning: Untethered high-speed 3d running of MIT cheetah 2 in 2015 IEEE International Conference on Robotics and Automation (IEEE 2015) pp. 5163\u20135170.","DOI":"10.1109\/ICRA.2015.7139918"},{"key":"e_1_3_2_46_2","unstructured":"Introducing wildcat https:\/\/youtu.be\/wE3fmFTtP9g [accessed 6 August 2018]."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2723931"},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","unstructured":"S. Shamsuddin L. I. Ismail H. Yussof N. I. Zahari S. Bahari H. Hashim A. Jaffar Humanoid robot Nao: Review of control and motion exploration in 2011 IEEE International Conference on Control System Computing and Engineering (IEEE 2011) pp. 511\u2013516.","DOI":"10.1109\/ICCSCE.2011.6190579"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1177\/02783640122067570"},{"key":"e_1_3_2_50_2","article-title":"Boston dynamics sand flea robot demonstrates astonishing jumping skills","volume":"2","author":"Ackerman E.","year":"2012","unstructured":"E. Ackerman, Boston dynamics sand flea robot demonstrates astonishing jumping skills. IEEE Spectrum Robotics Blog 2, (2012).","journal-title":"IEEE Spectrum Robotics Blog"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(01)00113-0"},{"key":"e_1_3_2_52_2","first-page":"831","article-title":"Design of HyQ \u2013 a hydraulically and electrically actuated quadruped robot","volume":"225","author":"Semini C.","year":"2011","unstructured":"C. Semini, N. G. Tsagarakis, E. Guglielmino, M. Focchi, F. Cannella, D. G. Caldwell, Design of HyQ \u2013 a hydraulically and electrically actuated quadruped robot. Proc. Inst. Mec. Eng. Part I J. Syst. Control Eng. 225, 831\u2013849 (2011).","journal-title":"Proc. Inst. Mec. Eng. Part I J. Syst. Control Eng."},{"key":"e_1_3_2_53_2","doi-asserted-by":"crossref","unstructured":"N. G. Tsagarakis S. Morfey G. M. Cerda L. Zhibin D. G. Caldwell COMpliant huMANoid COMAN: Optimal joint stiffness tuning for modal frequency control in 2013 IEEE International Conference on Robotics and Automation (IEEE 2013) pp. 673\u2013678.","DOI":"10.1109\/ICRA.2013.6630645"},{"key":"e_1_3_2_54_2","unstructured":"J. Bergstra G. Desjardins P. Lamblin Y. Bengio Quadratic polynomials learn better image features. Technical report 1337 (2009)."},{"key":"e_1_3_2_55_2","unstructured":"J. Schulman P. Moritz S. Levine M. Jordan P. Abbeel High-dimensional continuous control using generalized advantage estimation in Proceedings of the International Conference on Learning Representations (ICLR) (2016)."},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"e_1_3_2_57_2","doi-asserted-by":"crossref","first-page":"17","DOI":"10.7551\/mitpress\/9816.003.0008","article-title":"State estimation for legged robots-consistent fusion of leg kinematics and imu","volume":"17","author":"Bloesch M.","year":"2013","unstructured":"M. Bloesch, M. Hutter, M. A. Hoepflinger, S. Leutenegger, C. Gehring, C. D. Remy, R. Siegwart, State estimation for legged robots-consistent fusion of leg kinematics and imu. Robotics 17, 17\u201324 (2013).","journal-title":"Robotics"},{"key":"e_1_3_2_58_2","doi-asserted-by":"crossref","unstructured":"X. B. Peng M. van de Panne Learning locomotion skills using deeprl: Does the choice of action space matter? in Proceedings of the ACM SIGGRAPH\/Eurographics Symposium on Computer Animation (ACM 2017) p. 12.","DOI":"10.1145\/3099564.3099567"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201397"},{"key":"e_1_3_2_60_2","doi-asserted-by":"crossref","unstructured":"Y. Bengio J. Louradour R. Collobert J. Weston Curriculum learning in Proceedings of the 26th annual International Conference on Machine Learning (ACM 2009) pp. 41\u201348.","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_2_61_2","unstructured":"G. A. Pratt M. M. Williamson Series elastic actuators in Proceedings 1995 IEEE\/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots\u2019 (IEEE 1995) pp. 399\u2013406."},{"key":"e_1_3_2_62_2","unstructured":"M. Hutter K. Bodie A. Lauber J. Hwangbo Joint unit joint system robot for manipulation and\/or transportation robotic exoskeleton system and method for manipulation and\/or transportation EP16181251 (2016)."}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1126\/scirobotics.aau5872","content-type":"unspecified","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.aau5872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T12:22:46Z","timestamp":1705407766000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.aau5872"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,30]]},"references-count":61,"journal-issue":{"issue":"26","published-print":{"date-parts":[[2019,1,30]]}},"alternative-id":["10.1126\/scirobotics.aau5872"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.aau5872","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1,30]]},"article-number":"eaau5872"}}