{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T20:41:06Z","timestamp":1767818466519,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2042"],"award-info":[{"award-number":["U22B2042"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,21]]},"DOI":"10.1145\/3772429.3772430","type":"proceedings-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T13:59:08Z","timestamp":1766498348000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Embodied Quadruped Agents for Posture-Aware Locomotion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7633-0411","authenticated-orcid":false,"given":"Xiangyu","family":"Miao","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5535-9104","authenticated-orcid":false,"given":"Jun","family":"Sun","sequence":"additional","affiliation":[{"name":"Shanghai Aerospace Control Technology Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1000-3232","authenticated-orcid":false,"given":"Hang","family":"Lai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7942-1312","authenticated-orcid":false,"given":"Xinpeng","family":"Di","sequence":"additional","affiliation":[{"name":"Shanghai Aerospace Control Technology Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7437-1977","authenticated-orcid":false,"given":"Jiahang","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0281-8271","authenticated-orcid":false,"given":"Yong","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0127-2425","authenticated-orcid":false,"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,23]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_1_3_2","first-page":"403","volume-title":"Conference on robot learning","author":"Agarwal Ananye","year":"2023","unstructured":"Ananye Agarwal, Ashish Kumar, Jitendra Malik, and Deepak Pathak. 2023. Legged locomotion in challenging terrains using egocentric vision. In Conference on robot learning. PMLR, 403\u2013415."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Guillaume Bellegarda and Auke Ijspeert. 2022. CPG-RL: Learning central pattern generators for quadruped locomotion. IEEE Robotics and Automation Letters 7 4 (2022) 12547\u201312554.","DOI":"10.1109\/LRA.2022.3218167"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611128"},{"key":"e_1_3_3_1_6_2","first-page":"66","volume-title":"Conference on robot learning","author":"Chen Dian","year":"2020","unstructured":"Dian Chen, Brady Zhou, Vladlen Koltun, and Philipp Kr\u00e4henb\u00fchl. 2020. Learning by cheating. In Conference on robot learning. PMLR, 66\u201375."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981973"},{"key":"e_1_3_3_1_8_2","first-page":"17273","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Fu Zipeng","year":"2022","unstructured":"Zipeng Fu, Ashish Kumar, Ananye Agarwal, Haozhi Qi, Jitendra Malik, and Deepak Pathak. 2022. Coupling vision and proprioception for navigation of legged robots. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17273\u201317283."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Siddhant Gangapurwala Mathieu Geisert Romeo Orsolino Maurice Fallon and Ioannis Havoutis. 2022. Rloc: Terrain-aware legged locomotion using reinforcement learning and optimal control. IEEE Transactions on Robotics 38 5 (2022) 2908\u20132927.","DOI":"10.1109\/TRO.2022.3172469"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Siddhant Gangapurwala Alexander Mitchell and Ioannis Havoutis. 2020. Guided constrained policy optimization for dynamic quadrupedal robot locomotion. IEEE Robotics and Automation Letters 5 2 (2020) 3642\u20133649.","DOI":"10.1109\/LRA.2020.2979656"},{"key":"e_1_3_3_1_11_2","unstructured":"Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Jemin Hwangbo Joonho Lee Alexey Dosovitskiy Dario Bellicoso Vassilios Tsounis Vladlen Koltun and Marco Hutter. 2019. Learning agile and dynamic motor skills for legged robots. Science Robotics 4 26 (2019) eaau5872.","DOI":"10.1126\/scirobotics.aau5872"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Gwanghyeon Ji Juhyeok Mun Hyeongjun Kim and Jemin Hwangbo. 2022. Concurrent training of a control policy and a state estimator for dynamic and robust legged locomotion. IEEE Robotics and Automation Letters 7 2 (2022) 4630\u20134637.","DOI":"10.1109\/LRA.2022.3151396"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Chengxing Jia Fuxiang Zhang Tian Xu Jingcheng Pang Zongzhang Zhang and Yang Yu. 2024. Model gradient: unified model and policy learning in model-based reinforcement learning. Frontiers of Computer Science 18 (2024) 184339\u2013. 10.1007\/s11704-023-3150-5","DOI":"10.1007\/s11704-023-3150-5"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635838"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Yunho Kim Hyunsik Oh Jeonghyun Lee Jinhyeok Choi Gwanghyeon Ji Moonkyu Jung Donghoon Youm and Jemin Hwangbo. 2024. Not only rewards but also constraints: Applications on legged robot locomotion. IEEE Transactions on Robotics (2024).","DOI":"10.1109\/TRO.2024.3400935"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Ashish Kumar Zipeng Fu Deepak Pathak and Jitendra Malik. 2021. Rma: Rapid motor adaptation for legged robots. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.04034 (2021).","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160497"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Joonho Lee Jemin Hwangbo Lorenz Wellhausen Vladlen Koltun and Marco Hutter. 2020. Learning quadrupedal locomotion over challenging terrain. Science robotics 5 47 (2020) eabc5986.","DOI":"10.1126\/scirobotics.abc5986"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Timoth\u00e9e Lesort Vincenzo Lomonaco Andrei Stoian Davide Maltoni David Filliat and Natalia D\u00edaz-Rodr\u00edguez. 2020. Continual learning for robotics: Definition framework learning strategies opportunities and challenges. Information fusion 58 (2020) 52\u201368.","DOI":"10.1016\/j.inffus.2019.12.004"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Tianyu Li Jungdam Won Jeongwoo Cho Sehoon Ha and Akshara Rai. 2023. Fastmimic: Model-based motion imitation for agile diverse and generalizable quadrupedal locomotion. Robotics 12 3 (2023) 90.","DOI":"10.3390\/robotics12030090"},{"key":"e_1_3_3_1_22_2","unstructured":"Viktor Makoviychuk Lukasz Wawrzyniak Yunrong Guo Michelle Lu Kier Storey Miles Macklin David Hoeller Nikita Rudin Arthur Allshire Ankur Handa et\u00a0al. 2021. Isaac gym: High performance gpu-based physics simulation for robot learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.10470 (2021)."},{"key":"e_1_3_3_1_23_2","first-page":"22","volume-title":"Conference on Robot Learning","author":"Margolis Gabriel\u00a0B","year":"2023","unstructured":"Gabriel\u00a0B Margolis and Pulkit Agrawal. 2023. Walk these ways: Tuning robot control for generalization with multiplicity of behavior. In Conference on Robot Learning. PMLR, 22\u201331."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Gabriel\u00a0B Margolis Ge Yang Kartik Paigwar Tao Chen and Pulkit Agrawal. 2024. Rapid locomotion via reinforcement learning. The International Journal of Robotics Research 43 4 (2024) 572\u2013587.","DOI":"10.1177\/02783649231224053"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Takahiro Miki Joonho Lee Jemin Hwangbo Lorenz Wellhausen Vladlen Koltun and Marco Hutter. 2022. Learning robust perceptive locomotion for quadrupedal robots in the wild. Science robotics 7 62 (2022) eabk2822.","DOI":"10.1126\/scirobotics.abk2822"},{"key":"e_1_3_3_1_26_2","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1312.5602 (2013)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161144"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"T\u00f8nnes\u00a0F Nygaard Charles\u00a0P Martin Jim Torresen Kyrre Glette and David Howard. 2021. Real-world embodied AI through a morphologically adaptive quadruped robot. Nature Machine Intelligence 3 5 (2021) 410\u2013419.","DOI":"10.1038\/s42256-021-00320-3"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Lerrel Pinto Marcin Andrychowicz Peter Welinder Wojciech Zaremba and Pieter Abbeel. 2017. Asymmetric actor critic for image-based robot learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1710.06542 (2017).","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Niraj Rathod Angelo Bratta Michele Focchi Mario Zanon Octavio Villarreal Claudio Semini and Alberto Bemporad. 2021. Model predictive control with environment adaptation for legged locomotion. IEEE Access 9 (2021) 145710\u2013145727.","DOI":"10.1109\/ACCESS.2021.3118957"},{"key":"e_1_3_3_1_31_2","first-page":"91","volume-title":"Conference on Robot Learning","author":"Rudin Nikita","year":"2022","unstructured":"Nikita Rudin, David Hoeller, Philipp Reist, and Marco Hutter. 2022. Learning to walk in minutes using massively parallel deep reinforcement learning. In Conference on Robot Learning. PMLR, 91\u2013100."},{"key":"e_1_3_3_1_32_2","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1707.06347 (2017)."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Laura Smith Ilya Kostrikov and Sergey Levine. 2022. A walk in the park: Learning to walk in 20 minutes with model-free reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.07860 (2022).","DOI":"10.15607\/RSS.2023.XIX.056"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Jie Tan Tingnan Zhang Erwin Coumans Atil Iscen Yunfei Bai Danijar Hafner Steven Bohez and Vincent Vanhoucke. 2018. Sim-to-real: Learning agile locomotion for quadruped robots. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1804.10332 (2018).","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"e_1_3_3_1_37_2","unstructured":"Unitree. 2022. Unitree Robotics. https:\/\/www.unitree.com\/."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Jinze Wu Guiyang Xin Chenkun Qi and Yufei Xue. 2023. Learning robust and agile legged locomotion using adversarial motion priors. IEEE Robotics and Automation Letters 8 8 (2023) 4975\u20134982.","DOI":"10.1109\/LRA.2023.3290509"},{"key":"e_1_3_3_1_39_2","unstructured":"Jinze Wu Yufei Xue and Chenkun Qi. 2023. Learning multiple gaits within latent space for quadruped robots. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.03014 (2023)."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627676.3627686"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560837"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Chuanyu Yang Kai Yuan Qiuguo Zhu Wanming Yu and Zhibin Li. 2020. Multi-expert learning of adaptive legged locomotion. Science Robotics 5 49 (2020) eabb2174.","DOI":"10.1126\/scirobotics.abb2174"},{"key":"e_1_3_3_1_43_2","unstructured":"Ruihan Yang Minghao Zhang Nicklas Hansen Huazhe Xu and Xiaolong Wang. 2021. Learning vision-guided quadrupedal locomotion end-to-end with cross-modal transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.03996 (2021)."},{"key":"e_1_3_3_1_44_2","first-page":"773","volume-title":"Conference on Robot Learning","author":"Yang Yuxiang","year":"2022","unstructured":"Yuxiang Yang, Tingnan Zhang, Erwin Coumans, Jie Tan, and Byron Boots. 2022. Fast and efficient locomotion via learned gait transitions. In Conference on Robot Learning. PMLR, 773\u2013783."},{"key":"e_1_3_3_1_45_2","unstructured":"Wangyang Yue Yuan Zhou Xiaochuan Zhang Yuchen Hua Zhiyuan Wang and Guang Kou. 2022. Aacc: Asymmetric actor-critic in contextual reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.02376 (2022)."},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611254"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"e_1_3_3_1_48_2","unstructured":"Ziwen Zhuang Zipeng Fu Jianren Wang Christopher Atkeson Soeren Schwertfeger Chelsea Finn and Hang Zhao. 2023. Robot parkour learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.05665 (2023)."}],"event":{"name":"DAI '25: The Seventh International Conference on Distributed Artificial Intelligence","location":"London United Kingdom","acronym":"DAI '25"},"container-title":["Proceedings of the 2025 The Seventh International Conference on Distributed Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772429.3772430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T19:42:48Z","timestamp":1767814968000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772429.3772430"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,21]]},"references-count":47,"alternative-id":["10.1145\/3772429.3772430","10.1145\/3772429"],"URL":"https:\/\/doi.org\/10.1145\/3772429.3772430","relation":{},"subject":[],"published":{"date-parts":[[2025,11,21]]},"assertion":[{"value":"2025-12-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}