{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T12:09:21Z","timestamp":1761480561915,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819520978"},{"type":"electronic","value":"9789819520985"}],"license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-2098-5_59","type":"book-chapter","created":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T12:00:50Z","timestamp":1761480050000},"page":"698-710","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Whole-Body Motion Control Through Instruction Learning and\u00a0Human Motion Data"],"prefix":"10.1007","author":[{"given":"Zhipeng","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaixuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linqi","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boyang","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"59_CR1","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"59_CR2","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning (ICML), pp. 1861\u20131870. PMLR (2018)"},{"key":"59_CR3","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning (ICML), pp. 41\u201348 (2009)","DOI":"10.1145\/1553374.1553380"},{"issue":"1\u20132","key":"59_CR4","first-page":"1","volume":"7","author":"T Osa","year":"2018","unstructured":"Osa, T., Pajarinen, J., Neumann, G., Bagnell, J.A., Abbeel, P., Peters, J.: An algorithmic perspective on imitation learning. Found. Trends Robot. 7(1\u20132), 1\u2013179 (2018)","journal-title":"Found. Trends Robot."},{"key":"59_CR5","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1109\/TIE.2007.891642","volume":"54","author":"T Takeda","year":"2007","unstructured":"Takeda, T., Hirata, Y., Kosuge, K.: Dance step estimation method based on HMM for dance partner robot. IEEE Trans. Industr. Electron. 54, 699\u2013706 (2007)","journal-title":"IEEE Trans. Industr. Electron."},{"issue":"4","key":"59_CR6","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1109\/TRO.2014.2304775","volume":"30","author":"A Gams","year":"2014","unstructured":"Gams, A., Nemec, B., Ijspeert, A.J., Ude, A.: Coupling movement primitives: Interaction with the environment and bimanual tasks. IEEE Trans. Rob. 30(4), 816\u2013830 (2014)","journal-title":"IEEE Trans. Rob."},{"key":"59_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, T., McCarthy, Z., Jow, O., Lee, D., Chen, X., Goldberg, K., Abbeel, P.: Deep imitation learning for complex manipulation tasks from virtual reality teleoperation. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 5628\u20135635 (2018)","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"59_CR8","unstructured":"Ng, A.Y., Russell, S.: Algorithms for inverse reinforcement learning. In: Proceedings of the 17th International Conference on Machine Learning (ICML), vol. 1, no. 2, p. 2 (2000)"},{"issue":"2\u20133","key":"59_CR9","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1177\/0278364918784350","volume":"38","author":"S Krishnan","year":"2019","unstructured":"Krishnan, S., et al.: SWIRL: a sequential windowed inverse reinforcement learning algorithm for robot tasks with delayed rewards. Int. J. Robot. Res. 38(2\u20133), 126\u2013145 (2019)","journal-title":"Int. J. Robot. Res."},{"issue":"4","key":"59_CR10","first-page":"1","volume":"37","author":"XB Peng","year":"2018","unstructured":"Peng, X.B., Abbeel, P., Levine, S., Panne, M.: DeepMimic: example-guided deep reinforcement learning of physics-based character skills. ACM Trans. Graphics (TOG) 37(4), 1\u201314 (2018)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"59_CR11","doi-asserted-by":"crossref","unstructured":"Kuefler, A., Morton, J., Wheeler, T., Kochenderfer, M.: Imitating driver behavior with generative adversarial networks. In: Proceedings of the IEEE Intelligent Vehicles Symposium (IV), pp. 204\u2013211. IEEE (2017)","DOI":"10.1109\/IVS.2017.7995721"},{"key":"59_CR12","unstructured":"Cai, Q., Hong, M., Chen, Y., Wang, Z.: On the global convergence of imitation learning: a case for linear quadratic regulator. arXiv preprint arXiv:1901.03674 (2019)"},{"key":"59_CR13","unstructured":"Peng, X.B., Coumans, E., Zhang, T., Lee, T.W., Tan, J., Levine, S.: Learning agile robotic locomotion skills by imitating animals. arXiv preprint arXiv:2004.00784 (2020)"},{"key":"59_CR14","unstructured":"Ye, L., Li, J., Cheng, Y., Wang, X., Liang, B., Peng, Y.: From knowing to doing: learning diverse motor skills through instruction learning. arXiv preprint arXiv:2309.09167 (2023)"},{"key":"59_CR15","unstructured":"Ye, L., et al.: Unity RL playground: a versatile reinforcement learning framework for mobile robots. arXiv preprint arXiv:2503.05146 (2025)"},{"key":"59_CR16","unstructured":"Juliani, A., et al.: Unity: a general platform for intelligent agents. arXiv preprint arXiv:1809.02627 (2018)"},{"key":"59_CR17","unstructured":"Liu, Q., Guo, J., Lin, S., Ma, S., Zhu, J., Li, Y.: MASQ: multi-agent reinforcement learning for single quadruped robot locomotion. arXiv preprint arXiv:2408.13759 (2024)"},{"key":"59_CR18","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Huang, H., Sun, S., Li, C., Xu, W.: Fusing dynamics and reinforcement learning for control strategy: achieving precise gait and high robustness in humanoid robot locomotion. In: Proceedings of the 2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids), pp. 1072\u20131079. IEEE (2024)","DOI":"10.1109\/Humanoids58906.2024.10769920"},{"issue":"9","key":"59_CR19","doi-asserted-by":"publisher","first-page":"548","DOI":"10.3390\/biomimetics9090548","volume":"9","author":"Q Zhou","year":"2024","unstructured":"Zhou, Q., Li, G., Tang, R., Xu, Y., Wen, H., Shi, Q.: Stable jumping control based on deep reinforcement learning for a locust-inspired robot. Biomimetics 9(9), 548 (2024)","journal-title":"Biomimetics"},{"key":"59_CR20","doi-asserted-by":"crossref","unstructured":"Darvish, K., et al.: Whole-body geometric retargeting for humanoid robots. In: 2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids), pp. 679\u2013686. IEEE (2019)","DOI":"10.1109\/Humanoids43949.2019.9035059"},{"key":"59_CR21","unstructured":"Cisneros-Lim\u00f3n, R., et al.: A cybernetic avatar system to embody human telepresence for connectivity, exploration, and skill transfer. Int. J. Soc. Robot., 1\u201328 (2024)"},{"key":"59_CR22","unstructured":"Radosavovic, I., Zhang, B., Shi, B., Rajasegaran, J., Kamat, S., Darrell, T., Malik, J.: Humanoid locomotion as next token prediction. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS) (2024)"},{"key":"59_CR23","doi-asserted-by":"crossref","unstructured":"He, T., et al.: Learning human-to-humanoid real-time whole-body teleoperation. In: 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8944\u20138951. IEEE (2024)","DOI":"10.1109\/IROS58592.2024.10801984"},{"key":"59_CR24","unstructured":"He, T., et al.: OmniH2O: universal and dexterous human-to-humanoid whole-body teleoperation and learning. arXiv preprint arXiv:2406.08858 (2024)"},{"key":"59_CR25","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: xAMASS: archive of motion capture as surface shapes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5442\u20135451 (2019)","DOI":"10.1109\/ICCV.2019.00554"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-2098-5_59","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T12:01:01Z","timestamp":1761480061000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-2098-5_59"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"ISBN":["9789819520978","9789819520985"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-2098-5_59","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"27 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okayama","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.icira2025.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}