{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:33:57Z","timestamp":1772120037563,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["B08043"],"award-info":[{"award-number":["B08043"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["B08043"],"award-info":[{"award-number":["B08043"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["B08043"],"award-info":[{"award-number":["B08043"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["B08043"],"award-info":[{"award-number":["B08043"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62073041"],"award-info":[{"award-number":["62073041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62073041"],"award-info":[{"award-number":["62073041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62073041"],"award-info":[{"award-number":["62073041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62073041"],"award-info":[{"award-number":["62073041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s13042-024-02407-w","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T08:01:53Z","timestamp":1729065713000},"page":"2537-2551","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Robust humanoid robot vehicle ingress with a finite state machine integrated with deep reinforcement learning"],"prefix":"10.1007","volume":"16","author":[{"given":"Chenzheng","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xuechao","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Zhangguo","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Yue","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Kehong","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Pierre","family":"Gergondet","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,16]]},"reference":[{"key":"2407_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-74666-1","volume-title":"The DARPA robotics challenge finals: humanoid robots to the rescue,","author":"M Spenko","year":"2018","unstructured":"Spenko M, Buerger S, Iagnemma K (2018) The DARPA robotics challenge finals: humanoid robots to the rescue, vol 121. Springer"},{"issue":"2","key":"2407_CR2","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/s10846-019-01130-x","volume":"99","author":"K Sohn","year":"2020","unstructured":"Sohn K, Jang G (2020) Ground vehicle driving by full sized humanoid. J Intell Robot Syst 99(2):407\u2013425","journal-title":"J Intell Robot Syst"},{"issue":"3","key":"2407_CR3","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/MRA.2020.2987805","volume":"27","author":"K Kawaharazuka","year":"2020","unstructured":"Kawaharazuka K, Tsuzuki K, Koga Y et al (2020) Toward autonomous driving by musculoskeletal humanoids: a study of developed hardware and learning-based software. IEEE Robot Autom Mag 27(3):84\u201396","journal-title":"IEEE Robot Autom Mag"},{"key":"2407_CR4","unstructured":"JRL (2018) mc_rtc. https:\/\/github.com\/jrl-umi3218\/mc_rtc. Accessed 19 May 2024"},{"key":"2407_CR5","unstructured":"Hoffman M, Shahriari B, Aslanides J, et\u00a0al (2020) Acme: a research framework for distributed reinforcement learning. arXiv preprint arXiv:2006.00979arXiv:abs\/2006.00979"},{"key":"2407_CR6","doi-asserted-by":"crossref","unstructured":"Todorov E, Erez T, Tassa Y (2012) Mujoco: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on intelligent robots and systems, IEEE, pp 5026\u20135033","DOI":"10.1109\/IROS.2012.6386109"},{"issue":"1","key":"2407_CR7","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s11370-015-0181-2","volume":"9","author":"K Sohn","year":"2016","unstructured":"Sohn K, Oh P (2016) Optimization of humanoid\u2019s motions under multiple constraints in vehicle ingress task. Intel Serv Robot 9(1):31\u201348","journal-title":"Intel Serv Robot"},{"issue":"1","key":"2407_CR8","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10846-018-0835-3","volume":"95","author":"K Sohn","year":"2019","unstructured":"Sohn K (2019) Optimization of vehicle mounting motions and its application to full-sized humanoid, drc-hubo. J Intell Robot Syst 95(1):19\u201346","journal-title":"J Intell Robot Syst"},{"key":"2407_CR9","unstructured":"Schulman J, Levine S, Abbeel P, et\u00a0al (2015) Trust region policy optimization. In: International Conference on machine learning, PMLR, pp 1889\u20131897"},{"key":"2407_CR10","unstructured":"Schulman J, Wolski F, Dhariwal P, et\u00a0al (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"},{"key":"2407_CR11","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, et\u00a0al (2015) Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971"},{"issue":"2","key":"2407_CR12","doi-asserted-by":"publisher","first-page":"2610","DOI":"10.1109\/LRA.2020.2972879","volume":"5","author":"C Yang","year":"2020","unstructured":"Yang C, Yuan K, Heng S et al (2020) Learning natural locomotion behaviors for humanoid robots using human bias. IEEE Robot Autom Lett 5(2):2610\u20132617","journal-title":"IEEE Robot Autom Lett"},{"key":"2407_CR13","doi-asserted-by":"crossref","unstructured":"Rodriguez D, Behnke S (2021) Deepwalk: omnidirectional bipedal gait by deep reinforcement learning. In: 2021 IEEE International Conference on robotics and automation (ICRA), IEEE, pp 3033\u20133039","DOI":"10.1109\/ICRA48506.2021.9561717"},{"issue":"4","key":"2407_CR14","first-page":"1","volume":"37","author":"XB Peng","year":"2018","unstructured":"Peng XB, Abbeel P, Levine S et al (2018) Deepmimic: example-guided deep reinforcement learning of physics-based character skills. ACM Trans Graph (TOG) 37(4):1\u201314","journal-title":"ACM Trans Graph (TOG)"},{"key":"2407_CR15","doi-asserted-by":"crossref","unstructured":"Sferrazza C, Huang DM, Lin X, et\u00a0al (2024) Humanoidbench: Simulated humanoid benchmark for whole-body locomotion and manipulation. arXiv preprint arXiv:2403.10506","DOI":"10.15607\/RSS.2024.XX.061"},{"issue":"89","key":"2407_CR16","doi-asserted-by":"publisher","first-page":"eadi9579","DOI":"10.1126\/scirobotics.adi9579","volume":"9","author":"I Radosavovic","year":"2024","unstructured":"Radosavovic I, Xiao T, Zhang B et al (2024) Real-world humanoid locomotion with reinforcement learning. Sci Robot 9(89):eadi9579","journal-title":"Sci Robot"},{"key":"2407_CR17","doi-asserted-by":"crossref","unstructured":"Johannink T, Bahl S, Nair A, et\u00a0al (2019) Residual reinforcement learning for robot control. In: 2019 International Conference on robotics and automation (ICRA), IEEE, pp 6023\u20136029","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"2407_CR18","doi-asserted-by":"crossref","unstructured":"Li Z, Cheng X, Peng XB, et\u00a0al (2021) Reinforcement learning for robust parameterized locomotion control of bipedal robots. In: 2021 IEEE International Conference on robotics and automation (ICRA), IEEE, pp 2811\u20132817","DOI":"10.1109\/ICRA48506.2021.9560769"},{"issue":"1","key":"2407_CR19","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/s10846-022-01619-y","volume":"105","author":"AF Muzio","year":"2022","unstructured":"Muzio AF, Maximo MR, Yoneyama T (2022) Deep reinforcement learning for humanoid robot behaviors. J Intell Robot Syst 105(1):12","journal-title":"J Intell Robot Syst"},{"issue":"3","key":"2407_CR20","doi-asserted-by":"publisher","first-page":"8006","DOI":"10.1109\/LRA.2022.3187253","volume":"7","author":"JR Guadarrama-Olvera","year":"2022","unstructured":"Guadarrama-Olvera JR, Kajita S, Cheng G (2022) Preemptive foot compliance to lower impact during biped robot walking over unknown terrain. IEEE Robot Autom Lett 7(3):8006\u20138011","journal-title":"IEEE Robot Autom Lett"},{"issue":"4","key":"2407_CR21","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MRA.2019.2943395","volume":"26","author":"A Kheddar","year":"2019","unstructured":"Kheddar A, Caron S, Gergondet P et al (2019) Humanoid robots in aircraft manufacturing: The airbus use cases. IEEE Robot Autom Mag 26(4):30\u201345","journal-title":"IEEE Robot Autom Mag"},{"issue":"2","key":"2407_CR22","doi-asserted-by":"publisher","first-page":"1840","DOI":"10.1109\/LRA.2021.3060728","volume":"6","author":"M Murooka","year":"2021","unstructured":"Murooka M, Kumagai I, Morisawa M et al (2021) Humanoid loco-manipulation planning based on graph search and reachability maps. IEEE Robot Autom Lett 6(2):1840\u20131847","journal-title":"IEEE Robot Autom Lett"},{"issue":"1","key":"2407_CR23","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1109\/TRO.2018.2876782","volume":"35","author":"K Bouyarmane","year":"2018","unstructured":"Bouyarmane K, Chappellet K, Vaillant J et al (2018) Quadratic programming for multirobot and task-space force control. IEEE Trans Rob 35(1):64\u201377","journal-title":"IEEE Trans Rob"},{"key":"2407_CR24","doi-asserted-by":"crossref","unstructured":"Bouyarmane K, Kheddar A (2011) Using a multi-objective controller to synthesize simulated humanoid robot motion with changing contact configurations. In: 2011 IEEE\/RSJ International Conference on intelligent robots and systems, IEEE, pp 4414\u20134419","DOI":"10.1109\/IROS.2011.6094483"},{"key":"2407_CR25","doi-asserted-by":"crossref","unstructured":"Kajita S, Morisawa M, Miura K, et\u00a0al (2010) Biped walking stabilization based on linear inverted pendulum tracking. In: 2010 IEEE\/RSJ International Conference on intelligent robots and systems, IEEE, pp 4489\u20134496","DOI":"10.1109\/IROS.2010.5651082"},{"issue":"3","key":"2407_CR26","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1109\/TRO.2013.2296332","volume":"30","author":"A Escande","year":"2014","unstructured":"Escande A, Miossec S, Benallegue M et al (2014) A strictly convex hull for computing proximity distances with continuous gradients. IEEE Trans Rob 30(3):666\u2013678","journal-title":"IEEE Trans Rob"},{"key":"2407_CR27","volume-title":"Nonlinear control","author":"HK Khalil","year":"2015","unstructured":"Khalil HK (2015) Nonlinear control, vol 406. Pearson, New York"},{"key":"2407_CR28","unstructured":"Popov I, Heess N, Lillicrap T, et\u00a0al (2017) Data-efficient deep reinforcement learning for dexterous manipulation. arXiv preprint arXiv:1704.03073"},{"issue":"4","key":"2407_CR29","doi-asserted-by":"publisher","first-page":"3247","DOI":"10.1109\/LRA.2018.2851148","volume":"3","author":"K Lobos-Tsunekawa","year":"2018","unstructured":"Lobos-Tsunekawa K, Leiva F, Ruiz-del Solar J (2018) Visual navigation for biped humanoid robots using deep reinforcement learning. IEEE Robot Autom Lett 3(4):3247\u20133254","journal-title":"IEEE Robot Autom Lett"},{"key":"2407_CR30","unstructured":"Barth-Maron G, Hoffman MW, Budden D, et\u00a0al (2018) Distributed distributional deterministic policy gradients. arXiv preprint arXiv:1804.08617"},{"key":"2407_CR31","doi-asserted-by":"crossref","unstructured":"Singh RP, Gergondet P, Kanehiro F (2022) mc-mujoco: Simulating articulated robots with fsm controllers in mujoco. arXiv preprint arXiv:2209.00274","DOI":"10.1109\/SII55687.2023.10039218"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02407-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02407-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02407-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T03:32:41Z","timestamp":1743996761000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02407-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["2407"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02407-w","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3444385\/v1","asserted-by":"object"}]},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]},"assertion":[{"value":"14 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}