{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:31:47Z","timestamp":1784179907003,"version":"3.55.0"},"reference-count":64,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"49","funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/L016834\/1"],"award-info":[{"award-number":["EP\/L016834\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","award":["ICT1900349"],"award-info":[{"award-number":["ICT1900349"]}],"id":[{"id":"10.13039\/501100004835","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","award":["ICT20005"],"award-info":[{"award-number":["ICT20005"]}],"id":[{"id":"10.13039\/501100004835","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2020,12,16]]},"abstract":"<jats:p>A multi-expert learning architecture generates adaptive behaviors for the versatile locomotion of quadruped robots.<\/jats:p>","DOI":"10.1126\/scirobotics.abb2174","type":"journal-article","created":{"date-parts":[[2020,12,9]],"date-time":"2020-12-09T20:18:52Z","timestamp":1607545132000},"source":"Crossref","is-referenced-by-count":192,"title":["Multi-expert learning of adaptive legged locomotion"],"prefix":"10.1126","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9082-5193","authenticated-orcid":true,"given":"Chuanyu","family":"Yang","sequence":"first","affiliation":[{"name":"School of Informatics, University of Edinburgh, Edinburgh, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2349-4192","authenticated-orcid":true,"given":"Kai","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Informatics, University of Edinburgh, Edinburgh, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuguo","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5522-7937","authenticated-orcid":true,"given":"Wanming","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Informatics, University of Edinburgh, Edinburgh, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6357-7419","authenticated-orcid":true,"given":"Zhibin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Informatics, University of Edinburgh, Edinburgh, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1138353"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.2007.146605"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14045"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-019-0536-7"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1848"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"S. Gay J. Santos-Victor A. Ijspeert Learning robot gait stability using neural networks as sensory feedback function for central pattern generators in Proceedings of the 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2013) pp. 194\u2013201.","DOI":"10.1109\/IROS.2013.6696353"},{"key":"e_1_3_2_8_2","unstructured":"DARPA Robotics Challenge (DRC); https:\/\/www.darpa.mil\/program\/darpa-robotics-challenge."},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"C. G. Atkeson B. P. W. Babu N. Banerjee D. Berenson C. P. Bove X. Cui M. DeDonato R. Du S. Feng P. Franklin M. Gennert J. P. Graff P. He A. Jaeger J. Kim K. Knoedler L. Li C. Liu X. Long T. Padir F. Polido G. G. Tighe X. Xinjilefu No falls no resets: Reliable humanoid behavior in the DARPA Robotics Challenge in Proceedings of the 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) (IEEE 2015) pp. 623\u2013630.","DOI":"10.1109\/HUMANOIDS.2015.7363436"},{"key":"e_1_3_2_10_2","unstructured":"N. A. Bemstein The Co-Ordination and Regulation of Movements (Pergamon 1967)."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.humov.2009.11.002"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aav4282"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"D. Dimitrov A. Sherikov P. Wieber A sparse model predictive control formulation for walking motion generation in Proceedings of the 2011 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2011) pp. 2292\u20132299.","DOI":"10.1109\/IROS.2011.6095035"},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"H.-W. Park P. M. Wensing S. Kim Online planning for autonomous running jumps over obstacles in high-speed quadrupeds in Proceedings of Robotics: Science and Systems (RSS) (2015).","DOI":"10.15607\/RSS.2015.XI.047"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"J. Di Carlo P. M. Wensing B. Katz G. Bledt S. Kim Dynamic locomotion in the MIT Cheetah 3 through convex model-predictive control in Proceedings of the 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2018) pp. 1\u20139.","DOI":"10.1109\/IROS.2018.8594448"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21559"},{"key":"e_1_3_2_17_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\u2014A highly mobile and dynamic quadrupedal robot in Proceedings of the 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_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800124"},{"key":"e_1_3_2_19_2","doi-asserted-by":"crossref","unstructured":"H. Dai A. Valenzuela R. Tedrake Whole-body motion planning with centroidal dynamics and full kinematics in Proceedings of the 2014 IEEE-RAS International Conference on Humanoid Robots (Humanoids) (IEEE 2014) pp. 295\u2013302.","DOI":"10.1109\/HUMANOIDS.2014.7041375"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2798285"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010754"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0025-4"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"K. Bouyarmane S. Caron A. Escande A. Kheddar Multi-contact planning and control in Humanoid Robotics: A Reference (Springer 2019) pp. 1763\u20131804.","DOI":"10.1007\/978-94-007-6046-2_32"},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","unstructured":"B. Siciliano O. Khatib Springer Handbook of Robotics (Springer 2016).","DOI":"10.1007\/978-3-319-32552-1"},{"key":"e_1_3_2_26_2","unstructured":"M. Posa thesis Massachusetts Institute of Technology (2017)."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","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 in Proceedings of Robotics: Science and Systems (RSS) (2018).","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"e_1_3_2_31_2","doi-asserted-by":"crossref","unstructured":"T. Li H. Geyer C. G. Atkeson A. Rai Using deep reinforcement learning to learn high-level policies on the ATRIAS biped in Proceedings of the 2019 International Conference on Robotics and Automation (ICRA) (IEEE 2019) pp. 263\u2013269.","DOI":"10.1109\/ICRA.2019.8793864"},{"key":"e_1_3_2_32_2","unstructured":"Z. Xie P. Clary J. Dao P. Morais J. Hurst M. Panne Learning locomotion skills for Cassie: Iterative design and sim-to-real in Proceedings of the Conference on Robot Learning (CoRL) (PMLR 2020) pp. 100:317\u2013329."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"e_1_3_2_35_2","unstructured":"K. Frans J. Ho X. Chen P. Abbeel J. Schulman Meta learning shared hierarchies in Proceedings of the 2018 International Conference on Learning Representations (ICLR) (2018)."},{"key":"e_1_3_2_36_2","unstructured":"J. Merel A. Ahuja V. Pham S. Tunyasuvunakool S. Liu D. Tirumala N. Heess G. Wayne Hierarchical visuomotor control of humanoids in Proceedings of the 2018 International Conference on Learning Representations (ICLR) (2018)."},{"key":"e_1_3_2_37_2","unstructured":"T. Haarnoja K. Hartikainen P. Abbeel S. Levine Latent space policies for hierarchical reinforcement learning in Proceedings of the 35th International Conference on Machine Learning (PMLR 2018) pp. 1851\u20131860."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912472380"},{"key":"e_1_3_2_40_2","doi-asserted-by":"crossref","unstructured":"X. Chang T. M. Hospedales T. Xiang Multi-level factorisation net for person re-identification in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2018) pp. 2109\u20132118.","DOI":"10.1109\/CVPR.2018.00225"},{"key":"e_1_3_2_41_2","unstructured":"X. B. Peng M. Chang G. Zhang P. Abbeel S. Levine MCP: Learning composable hierarchical control with multiplicative compositional policies in Advances in Neural Information Processing Systems (Curran Associates Inc. 2019) pp. 3686\u20133697."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201366"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0079-6123(06)65017-6"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X00072538"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"F. L. Moro N. G. Tsagarakis D. G. Caldwell A human-like walking for the COmpliant huMANoid COMAN based on CoM trajectory reconstruction from kinematic Motion Primitives in Proceedings of the 2011 11th IEEE-RAS International Conference on Humanoid Robots (Humanoids) (IEEE 2011) pp. 364\u2013370.","DOI":"10.1109\/Humanoids.2011.6100862"},{"key":"e_1_3_2_46_2","first-page":"27","article-title":"Kinematic primitives for walking and trotting gaits of a quadruped robot with compliant legs","volume":"8","author":"Sprowitz A. T.","year":"2014","unstructured":"A. T. Sprowitz, M. Ajallooeian, A. Tuleu, A. J. Ijspeert, Kinematic primitives for walking and trotting gaits of a quadruped robot with compliant legs. Front. Comput. Neurosci. 8, 27 (2014).","journal-title":"Front. Comput. Neurosci."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073663"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356505"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2008.927693"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/s003590050108"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1242\/jeb.202.5.631"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaq0560"},{"key":"e_1_3_2_53_2","unstructured":"Jueying\u00ae | DeepRobotics; http:\/\/www.deeprobotics.cn\/default\/details."},{"key":"e_1_3_2_54_2","unstructured":"T. Haarnoja A. Zhou P. Abbeel S. Levine Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor in Proceedings of the 35th International Conference on Machine Learning (ICML) (PMLR 2018) pp. 1861\u20131870."},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972879"},{"key":"e_1_3_2_56_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) pp. 12:1\u201312:13.","DOI":"10.1145\/3099564.3099567"},{"key":"e_1_3_2_57_2","doi-asserted-by":"crossref","unstructured":"A. Rupam Mahmood D. Korenkevych B. J. Komer J. Bergstra Setting up a reinforcement learning task with a real-world robot in Proceedings of the 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2018) pp. 4635\u20134640.","DOI":"10.1109\/IROS.2018.8593894"},{"key":"e_1_3_2_58_2","unstructured":"H. van Hasselt Double Q-learning in Proceedings of the 23rd International Conference on Neural Information Processing Systems (Curran Associates Inc. 2010) pp. 2613\u20132621."},{"key":"e_1_3_2_59_2","doi-asserted-by":"crossref","unstructured":"H. Van Hasselt A. Guez D. Silver Deep reinforcement learning with double Q-learning in Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI 2016) pp. 2094\u20132100.","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-012-0527-1"},{"key":"e_1_3_2_61_2","doi-asserted-by":"crossref","unstructured":"E. Spyrakos-Papastavridis N. Kashiri J. Lee N. G. Tsagarakis D. G. Caldwell Online impedance parameter tuning for compliant biped balancing in Proceedings of the 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) (IEEE 2015) pp. 210\u2013216.","DOI":"10.1109\/HUMANOIDS.2015.7363553"},{"key":"e_1_3_2_62_2","doi-asserted-by":"crossref","unstructured":"C. Yang K. Yuan W. Merkt T. Komura S. Vijayakumar Z. Li Learning whole-body motor skills for humanoids in Proceedings of the 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids) (IEEE 2018) pp. 270\u2013276.","DOI":"10.1109\/HUMANOIDS.2018.8625045"},{"key":"e_1_3_2_63_2","unstructured":"Y. Hashiguchi K. Takaoka M. Kanemaru The development of a practical dexterous assembly robot system without the use of force sensor in Proceedings of the 2001 IEEE International Symposium on Assembly and Task Planning (ISATP2001). Assembly and Disassembly in the Twenty-first Century. (Cat. No.01TH8560) (IEEE 2001) pp. 470\u2013475."},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2745407"},{"key":"e_1_3_2_65_2","unstructured":"E. Coumans Y. Bai PyBullet a Python module for physics simulation for games robotics and machine learning; http:\/\/pybullet.org."}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1126\/scirobotics.abb2174","content-type":"unspecified","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.abb2174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T12:31:35Z","timestamp":1705408295000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.abb2174"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,16]]},"references-count":64,"journal-issue":{"issue":"49","published-print":{"date-parts":[[2020,12,16]]}},"alternative-id":["10.1126\/scirobotics.abb2174"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.abb2174","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,16]]},"article-number":"eabb2174"}}