{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T17:45:42Z","timestamp":1781545542486,"version":"3.54.5"},"reference-count":49,"publisher":"Informa UK Limited","issue":"8","funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"crossref","award":["JP20H04265"],"award-info":[{"award-number":["JP20H04265"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Advanced Robotics"],"published-print":{"date-parts":[[2024,4,17]]},"DOI":"10.1080\/01691864.2024.2336253","type":"journal-article","created":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T07:56:05Z","timestamp":1712303765000},"page":"541-561","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":2,"title":["Constrained footstep planning using model-based reinforcement learning in virtual constraint-based walking"],"prefix":"10.1080","volume":"38","author":[{"given":"Takanori","family":"Jin","sequence":"first","affiliation":[{"name":"Informatics, National Institute of informatics\/The Graduate Institute for Advanced Studies, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3760-249X","authenticated-orcid":false,"given":"Taisuke","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"Informatics, National Institute of informatics\/The Graduate Institute for Advanced Studies, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[{"name":"Information Science, Nara Institute of Science and Technology, Nara, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2024,4,5]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1991.131811"},{"key":"e_1_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2003.1241826"},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910379882"},{"key":"e_1_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2009.2024565"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.02.005"},{"key":"e_1_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-016-2645-0"},{"key":"e_1_3_2_8_1","doi-asserted-by":"crossref","unstructured":"Raibert MH Brown HB Chepponis M et\u00a0al. Dynamically stable legged locomotion (September 1985\u2013September 1989). USA. Massachusetts Institute of Technology; 1989.","DOI":"10.21236\/ADA225713"},{"key":"e_1_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2006.321385"},{"key":"e_1_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2405592"},{"key":"e_1_3_2_11_1","volume-title":"Model predictive control","author":"Camacho EF","year":"2013","unstructured":"Camacho EF, Alba CB. Model predictive control. Springer science & business media; 2013."},{"key":"e_1_3_2_12_1","unstructured":"Bhardwaj M Sundaralingam B Mousavian A et\u00a0al. STORM: an integrated framework for fast joint-space model-predictive control for reactive manipulation. In: 5th Annual Conference on Robot Learning; 2021."},{"key":"e_1_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196673"},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"e_1_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2009.2032777"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105151"},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487320"},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798370"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918791718"},{"key":"e_1_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912452673"},{"key":"e_1_3_2_21_1","doi-asserted-by":"crossref","unstructured":"Shafiee M Romualdi G Dafarra S et\u00a0al. Online DCM trajectory generation for push recovery of torque-controlled humanoid robots. In: 2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids); 2019. p. 671\u2013678.","DOI":"10.1109\/Humanoids43949.2019.9034996"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004796"},{"key":"e_1_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.8860"},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2002.806653"},{"key":"e_1_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799218"},{"key":"e_1_3_2_26_1","unstructured":"Silver T Allen K Tenenbaum J et\u00a0al. Residual policy learning arXiv preprint arXiv:181206298. 2018."},{"key":"e_1_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593722"},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561814"},{"key":"e_1_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812015"},{"key":"e_1_3_2_30_1","unstructured":"Yang Y Caluwaerts K Iscen A et\u00a0al. Data efficient reinforcement learning for legged robots. In: Conference on Robot Learning; 2019."},{"key":"e_1_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2007.380654"},{"key":"e_1_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105246"},{"key":"e_1_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3303786"},{"key":"e_1_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010091220143"},{"key":"e_1_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"e_1_3_2_36_1","unstructured":"Chua K Calandra R McAllister R et\u00a0al. Deep reinforcement learning in a handful of trials using probabilistic dynamics models. In: Advances in Neural Information Processing Systems; Vol. 31. Curran Associates Inc.; 2018."},{"key":"e_1_3_2_37_1","unstructured":"Osband I Aslanides J Cassirer A. Randomized prior functions for deep reinforcement learning. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems; Red Hook NY USA: Curran Associates Inc.; 2018. p. 8626\u20138638."},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.20965\/jrm.2012.p0866"},{"key":"e_1_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1163\/016918610X493552"},{"key":"e_1_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562093"},{"key":"e_1_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.v4.2"},{"key":"e_1_3_2_42_1","unstructured":"Coumans E Bai Y. Pybullet a python module for physics simulation for games robotics and machine learning [http:\/\/pybullet.org]; 2016\u20132021."},{"key":"e_1_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2006.321375"},{"key":"e_1_3_2_44_1","unstructured":"Julian R Swanson B Sukhatme G et\u00a0al. Never stop learning: the effectiveness of fine-tuning in robotic reinforcement learning. In: Proceedings of the 2020 Conference on Robot Learning; Vol. 155. PMLR; 2021. p. 2120\u20132136."},{"key":"e_1_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812166"},{"key":"e_1_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.09.006"},{"key":"e_1_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2016.07.008"},{"key":"e_1_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2014.7041373"},{"key":"e_1_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids43949.2019.9035046"},{"key":"e_1_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8625025"}],"container-title":["Advanced Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01691864.2024.2336253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,25]],"date-time":"2024-05-25T04:20:19Z","timestamp":1716610819000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01691864.2024.2336253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,5]]},"references-count":49,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,4,17]]}},"alternative-id":["10.1080\/01691864.2024.2336253"],"URL":"https:\/\/doi.org\/10.1080\/01691864.2024.2336253","relation":{},"ISSN":["0169-1864","1568-5535"],"issn-type":[{"value":"0169-1864","type":"print"},{"value":"1568-5535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,5]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2023-10-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-13","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}