{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:27:42Z","timestamp":1787164062484,"version":"build-2736575974"},"reference-count":65,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"117","funder":[{"name":"Beijing Natural Science Foundation","award":["24L30170"],"award-info":[{"award-number":["24L30170"]}]},{"name":"Science and Technology Innovation 2030 Major Project","award":["2021ZD0201402"],"award-info":[{"award-number":["2021ZD0201402"]}]},{"name":"Science and Technology Innovation 2030 Major Project","award":["2021ZD0201401"],"award-info":[{"award-number":["2021ZD0201401"]}]},{"name":"Tsinghua University Initiative Scientific Research Program","award":["20257020011"],"award-info":[{"award-number":["20257020011"]}]}],"content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2026,8,19]]},"abstract":"<jats:p>Humanoid soccer poses a representative challenge for embodied intelligence, requiring robots to coordinate agile locomotion with unreliable visual perception in dynamic environments. However, existing systems typically rely on modular pipelines that separate perception from control or assume ideal sensing, making it difficult to achieve coherent and reactive behavior under real-world perceptual limitations. In this work, we present a unified reinforcement learning\u2013based controller that enables humanoid robots to learn vision-driven reactive soccer skills by directly coupling visual perception with locomotion control. The robot is trained in simulation to acquire soccer behaviors, and adversarial motion priors guide policy learning toward natural motion patterns. To support robust performance under imperfect sensing, we introduce an encoder-decoder architecture together with a virtual perception system that models key characteristics of onboard vision, exposing the policy to perceptual noise and detection failures during training. This design encourages the policy to internalize perceptual uncertainty and continuously adapt its motion in a closed loop. The resulting controller produces coordinated soccer behaviors using only onboard vision, including ball searching, chasing, and multidirectional kicking. It reduces ball position estimation error by 46% and shortens time-to-kick by up to 64% compared with a rule-based baseline, achieving around 90% kicking success in frontfield positions. Experiments across diverse environments and dynamic scenarios, including real RoboCup competitions, further demonstrate the robust performance of the controller. These results highlight the practical effectiveness of integrating perceptual uncertainty directly into policy learning for achieving reliable vision-driven behaviors in humanoid robots operating under real-world conditions.<\/jats:p>","DOI":"10.1126\/scirobotics.aed1152","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T17:58:11Z","timestamp":1787162291000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":0,"title":["Learning vision-driven reactive soccer skills for humanoid robots"],"prefix":"10.1126","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9687-6732","authenticated-orcid":true,"given":"Yushi","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing 100084, China."},{"name":"ByteDance Seed, Beijing 100080, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0869-0192","authenticated-orcid":true,"given":"Changsheng","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing 100084, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4460-6651","authenticated-orcid":true,"given":"Penghui","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing 100084, China."},{"name":"ByteDance Seed, Beijing 100080, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1651-2970","authenticated-orcid":true,"given":"Jianran","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Seed, Beijing 100080, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5170-6480","authenticated-orcid":true,"given":"Weijian","family":"Sun","sequence":"additional","affiliation":[{"name":"ByteDance Seed, Beijing 100080, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1935-8349","authenticated-orcid":true,"given":"Tong","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing 100084, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4731-9352","authenticated-orcid":true,"given":"Kechang","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Engineering, China Agricultural University, Beijing 100083, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8968-7229","authenticated-orcid":true,"given":"Biao","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Engineering, China Agricultural University, Beijing 100083, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4659-8948","authenticated-orcid":true,"given":"Yangang","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Seed, Beijing 100080, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9694-6957","authenticated-orcid":true,"given":"Mingguo","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing 100084, China."},{"name":"Beijing Key Laboratory of Embodied Intelligence Systems, Beijing 100084, China."},{"name":"Institute for Embodied Intelligence and Robotics, Tsinghua University, Beijing 100084, China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"H. Kitano M. Asada Y. Kuniyoshi I. Noda E. Osawa \u201cRoboCup: The robot world cup initiative\u201d in Proceedings of the First International Conference on Autonomous Agents (Association for Computing Machinery 1997) pp. 340\u2013347.","DOI":"10.1145\/267658.267738"},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","unstructured":"G. I. Fernandez Y. Liu C. Togashi K. Gillespie A. Zhu Q. Wang Y. Wang H. Nam S. Wang R. Hou M. Zhu A. Navghare A. Xu T. Zhu M. Sung Ahn A. Flores Alvarez J. Quan E. Hong D. W. Hong \u201cRoboCup 2024 adult-sized humanoid champions guide for hardware vision and strategy\u201d in RoboCup 2024: Robot World Cup XXVII (Springer 2025) pp. 502\u2013514.","DOI":"10.1007\/978-3-031-85859-8_43"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"M. Abreu L. P. Reis N. Lau \u201cLearning to run faster in a humanoid robot soccer environment through reinforcement learning\u201d in RoboCup 2019: Robot World Cup XXIII (Springer 2019) pp. 3\u201315.","DOI":"10.1007\/978-3-030-35699-6_1"},{"key":"e_1_3_2_5_2","unstructured":"S. Bohez S. Tunyasuvunakool P. Brakel F. Sadeghi L. Hasenclever Y. Tassa E. Parisotto J. Humplik T. Haarnoja R. Hafner M. Wulfmeier M. Neunert B. Moran N. Siegel A. Huber F. Romano N. Batchelor F. Casarini J. Merel R. Hadsell N. Heess Imitate and repurpose: Learning reusable robot movement skills from human and animal behaviors. arXiv:2203.17138 [cs.RO] (2022)."},{"key":"e_1_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Y. Ji G. B. Margolis P. Agrawal \u201cDribbleBot: Dynamic legged manipulation in the wild\u201d in IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2023) pp. 5155\u20135162.","DOI":"10.1109\/ICRA48891.2023.10160325"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"P. Ravichandar L. Krishna N. Sobanbabu Q. Nguyen \u201cPreferenced oracle guided multi-mode policies for dynamic bipedal loco-manipulation\u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2025) pp. 6600\u20136606.","DOI":"10.1109\/IROS60139.2025.11246602"},{"key":"e_1_3_2_8_2","unstructured":"S. Yin Y. Ze H.-X. Yu C. K. Liu J. Wu VisualMimic: Visual humanoid loco-manipulation via motion tracking and generation. arXiv:2509.20322 [cs.RO] (2025)."},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Y. Ji Z. Li Y. Sun X. B. Peng S. Levine G. Berseth K. Sreenath \u201cHierarchical reinforcement learning for precise soccer shooting skills using a quadrupedal robot\u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2022) pp. 1479\u20131486.","DOI":"10.1109\/IROS47612.2022.9981984"},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"X. Huang Z. Li Y. Xiang Y. Ni Y. Chi Y. Li L. Yang X. B. Peng K. Sreenath \u201cCreating a dynamic quadrupedal robotic goalkeeper with reinforcement learning\u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2023) pp. 2715\u20132722.","DOI":"10.1109\/IROS55552.2023.10341936"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-025-11151-3"},{"key":"e_1_3_2_12_2","unstructured":"Z. Su Y. Gao E. Lukas Y. Li J. Cai F. Talubah F. Gao C. Yu Z. Li Y. Wu K. Sreenath \u201cToward real-world cooperative and competitive soccer with quadrupedal robot teams\u201d in 9th Annual Conference on Robot Learning (OpenReview 2025); https:\/\/openreview.net\/forum?id=9lCTcsmZMV."},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8022"},{"key":"e_1_3_2_14_2","unstructured":"D. Tirumala M. Wulfmeier B. Moran S. Huang J. Humplik G. Lever T. Haarnoja L. Hasenclever A. Byravan N. Batchelor N. Sreendra K. Patel M. Gwira F. Nori M. Riedmiller N. Heess \u201cLearning robot soccer from egocentric vision with deep reinforcement learning\u201d in 8th Annual Conference on Robot Learning (OpenReview 2024); https:\/\/openreview.net\/forum?id=fC0wWeXsVm."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"D. Crowley J. Dao H. Duan K. Green J. Hurst A. Fern \u201cOptimizing bipedal locomotion for the 100m dash with comparison to human running\u201d in IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2023) pp. 12205\u201312211.","DOI":"10.1109\/ICRA48891.2023.10160436"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241285161"},{"key":"e_1_3_2_18_2","unstructured":"Z. Zhuang S. Yao H. Zhao \u201cHumanoid parkour learning\u201d in 8th Annual Conference on Robot Learning (OpenReview 2024); https:\/\/openreview.net\/forum?id=fs7ia3FqUM."},{"key":"e_1_3_2_19_2","doi-asserted-by":"crossref","unstructured":"T. Huang J. Ren H. Wang Z. Wang Q. Ben M. Wen X. Chen J. Li J. Pang \u201cLearning humanoid standing-up control across diverse postures\u201d in Proceedings of Robotics: Science and Systems (RSS Foundation 2025) 10.15607\/RSS.2025.XXI.064.","DOI":"10.15607\/RSS.2025.XXI.064"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"P. Chen Y. Wang C. Luo W. Cai M. Zhao \u201cHiFAR: Multi-stage curriculum learning for high-dynamics humanoid fall recovery\u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2025) pp. 2908\u20132915.","DOI":"10.1109\/IROS60139.2025.11245953"},{"key":"e_1_3_2_21_2","unstructured":"T. Zhang B. Zheng R. Nai Y. Hu Y.-J. Wang G. Chen F. Lin J. Li C. Hong K. Sreenath Y. Gao \u201cHuB: Learning extreme humanoid balance\u201d in 9th Annual Conference on Robot Learning (OpenReview 2025); https:\/\/openreview.net\/forum?id=FCpYuGtN4j."},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"W. Xie J. Han J. Zheng H. Li X. Liu J. Shi W. Zhang C. Bai X. Li \u201cKungfuBot: Physics-based humanoid whole-body control for learning highly-dynamic skills\u201d in Advances in Neural Information Processing Systems (Curran Associates Inc. 2025) vol. 38 pp. 62406\u201362433.","DOI":"10.52202\/085713-2089"},{"key":"e_1_3_2_23_2","unstructured":"Z. Chen M. Ji X. Cheng X. Peng X. B. Peng X. Wang GMT: General motion tracking for humanoid whole-body control. arXiv:2506.14770 [cs.RO] (2025)."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2026.3692091"},{"key":"e_1_3_2_25_2","unstructured":"W. Zeng S. Lu K. Yin X. Niu M. Dai J. Wang J. Pang Behavior foundation model for humanoid robots. arXiv:2509.13780 [cs.RO] (2025)."},{"key":"e_1_3_2_26_2","unstructured":"Z. Zhang J. Guo C. Chen J. Wang C. Lin Y. Lian H. Xue Z. Wang M. Liu J. Lyu H. Liu H. Wang L. Yi Track any motions under any disturbances. arXiv:2509.13833 [cs.RO] (2025)."},{"key":"e_1_3_2_27_2","unstructured":"C. Li M. Hutter A. Krause Feature-based vs. GAN-based learning from demonstrations: When and why. arXiv:2507.05906 [cs.LG] (2025)."},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201311","article-title":"DeepMimic: Example-guided deep reinforcement learning of physics-based character skills","volume":"37","author":"Peng X. B.","year":"2018","unstructured":"X. B. Peng, P. Abbeel, S. Levine, M. van de Panne, DeepMimic: Example-guided deep reinforcement learning of physics-based character skills. ACM Trans. Graph. 37, 1\u201314 (2018).","journal-title":"ACM Trans. Graph."},{"key":"e_1_3_2_29_2","unstructured":"A. Allshire H. Choi J. Zhang D. McAllister A. Zhang C. M. Kim T. Darrell P. Abbeel J. Malik A. Kanazawa \u201cVisual imitation enables contextual humanoid control\u201d in 9th Annual Conference on Robot Learning (OpenReview 2025); https:\/\/openreview.net\/forum?id=C6VxzSpjrv."},{"key":"e_1_3_2_30_2","unstructured":"Q. Liao T. E. Truong X. Huang Y. Gao G. Tevet K. Sreenath C. K. Liu BeyondMimic: From motion tracking to versatile humanoid control via guided diffusion. arXiv:2508.08241 [cs.RO] (2025)."},{"key":"e_1_3_2_31_2","unstructured":"Z. Zhang C. Li T. Miki M. Hutter \u201cMotion priors reimagined: Adapting flat-terrain skills for complex quadruped mobility\u201d in 9th Annual Conference on Robot Learning (OpenReview 2025); https:\/\/openreview.net\/forum?id=JXBm4Xfrvj."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3645662"},{"key":"e_1_3_2_33_2","unstructured":"D. Kang J. Cheng F. Zargarbashi T. Yoon S. Choi S. Coros Walk like dogs: Learning steerable imitation controllers for legged robots from unlabeled motion data. arXiv:2507.00677 [cs.RO] (2025)."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"A. Escontrela X. B. Peng W. Yu T. Zhang A. Iscen K. Goldberg P. Abbeel \u201cAdversarial motion priors make good substitutes for complex reward functions\u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2022) pp. 25\u201332.","DOI":"10.1109\/IROS47612.2022.9981973"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"E. Vollenweider M. Bjelonic V. Klemm N. Rudin J. Lee M. Hutter \u201cAdvanced skills through multiple adversarial motion priors in reinforcement learning\u201d in IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2023) pp. 5120\u20135126.","DOI":"10.1109\/ICRA48891.2023.10160751"},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","unstructured":"A. F. Alvarez F. Zargarbashi H. Liu S. Wang L. Edwards J. Anz A. Xu F. Shi S. Coros D. W. Hong \u201cLearning to walk in costume: Adversarial motion priors for aesthetically constrained humanoids\u201d in IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids) (IEEE 2025) pp. 593\u2013600.","DOI":"10.1109\/Humanoids65713.2025.11203191"},{"key":"e_1_3_2_38_2","unstructured":"K. Wen C. Li J. He M. Hutter \u201cConstrained style learning from imperfect demonstrations under task optimality\u201d in 9th Annual Conference on Robot Learning (OpenReview 2025); https:\/\/openreview.net\/forum?id=TFbT7kHD89."},{"key":"e_1_3_2_39_2","unstructured":"M. Arjovsky S. Chintala L. Bottou \u201cWasserstein generative adversarial networks\u201d in Proceedings of the 34th International Conference on Machine Learning (PMLR 2017) vol. 70 pp. 214\u2013223."},{"key":"e_1_3_2_40_2","unstructured":"I. Gulrajani F. Ahmed M. Arjovsky V. Dumoulin A. Courville \u201cImproved training of Wasserstein GANs\u201d in Advances in Neural Information Processing Systems 30 I. Guyon U. Von Luxburg S. Bengio H. Wallach R. Fergus S. Vishwanathan R. Garnett Eds. (Curran Associates Inc. 2017) pp. 5769\u20135779."},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"A. Tang T. Hiraoka N. Hiraoka F. Shi K. Kawaharazuka K. Kojima K. Okada M. Inaba \u201cHumanMimic: Learning natural locomotion and transitions for humanoid robot via Wasserstein adversarial imitation\u201d in IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2024) pp. 13107\u201313114.","DOI":"10.1109\/ICRA57147.2024.10610449"},{"key":"e_1_3_2_42_2","unstructured":"Y. Zhang Y. Yuan P. Gurunath I. Gupta S. Omidshafiei A.-a. Agha-mohammadi M. Vazquez-Chanlatte L. Pedersen T. He G. Shi \u201cFALCON: Learning force-adaptive humanoid loco-manipulation\u201d in Proceedings of the 8th Annual Learning for Dynamics and Control Conference (PMLR 2026) vol. 331 pp. 265\u2013281."},{"key":"e_1_3_2_43_2","unstructured":"J. Jang Z. Wang Z. Zhou F. Wu Y. Zhao SEEC: Stable end-effector control with model-enhanced residual learning for humanoid loco-manipulation. arXiv:2509.21231 [cs.RO] (2025)."},{"key":"e_1_3_2_44_2","doi-asserted-by":"crossref","unstructured":"A.-C. Cheng Y. Ji Z. Yang Z. Gongye X. Zou J. Kautz E. Biyik H. Yin S. Liu X. Wang \u201cNaVILA: Legged robot vision-language-action model for navigation\u201d in Proceedings of Robotics: Science and Systems (RSS Foundation 2025) 10.15607\/RSS.2025.XXI.018.","DOI":"10.15607\/RSS.2025.XXI.018"},{"key":"e_1_3_2_45_2","unstructured":"Y. Seo C. Sferrazza H. Geng M. Nauman Z.-H. Yin P. Abbeel FastTD3: Simple fast and capable reinforcement learning for humanoid control. arXiv:2505.22642 [cs.RO] (2025)."},{"key":"e_1_3_2_46_2","unstructured":"Y. Wang P. Chen X. Han F. Wu M. Zhao Booster Gym: An end-to-end reinforcement learning framework for humanoid robot locomotion. arXiv:2506.15132 [cs.RO] (2025)."},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","unstructured":"K. Zakka B. Tabanpour Q. Liao M. Haiderbhai S. Holt J. Y. Luo A. Allshire E. Frey K. Sreenath L. A. Kahrs C. Sferrazza Y. Tassa P. Abbeel \u201cDemonstrating MuJoCo playground\u201d in Proceedings of Robotics: Science and Systems (RSS Foundation 2025) 10.15607\/RSS.2025.XXI.020.","DOI":"10.15607\/RSS.2025.XXI.020"},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","unstructured":"H. Geng F. Wang S. Wei Y. Li B. Wang B. An H. Lou C. T. Cheng P. Li H. Chen Y. Liang Y. Qian J. Mao W. Wan Y. Geng M. Zhang J. Lyu S. Zhao J. Zhang C. Xu J. Zhang C. Zhao H. Lu Y. Ding R. Gong Y. Wang Y. Kuang R. Wu B. Jia H. Dong S. Huang Y. Wang J. Malik P. Abbeel \u201cRoboVerse: A unified platform benchmark and dataset for scalable and generalizable robot learning\u201d in Proceedings of Robotics: Science and Systems (RSS Foundation 2025) 10.15607\/RSS.2025.XXI.022.","DOI":"10.15607\/RSS.2025.XXI.022"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-024-00363-x"},{"key":"e_1_3_2_50_2","doi-asserted-by":"crossref","unstructured":"L. Pinto M. Andrychowicz P. Welinder W. Zaremba P. Abbeel Asymmetric actor critic for image-based robot learning. arXiv:1710.06542 [cs.RO] (2017).","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"e_1_3_2_51_2","unstructured":"J. Schulman F. Wolski P. Dhariwal A. Radford O. Klimov Proximal policy optimization algorithms. arXiv:1707.06347 [cs.LG] (2017)."},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"e_1_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Z. Li X. B. Peng P. Abbeel S. Levine G. Berseth K. Sreenath \u201cRobust and versatile bipedal jumping control through reinforcement learning\u201d in Proceedings of Robotics: Science and Systems (RSS Foundation 2023) 10.15607\/RSS.2023.XIX.052.","DOI":"10.15607\/RSS.2023.XIX.052"},{"key":"e_1_3_2_54_2","doi-asserted-by":"crossref","unstructured":"X. Gu Y.-J. Wang X. Zhu C. Shi Y. Guo Y. Liu J. Chen \u201cAdvancing humanoid locomotion: Mastering challenging terrains with denoising world model learning\u201d in Proceedings of Robotics: Science and Systems (RSS Foundation 2024) 10.15607\/RSS.2024.XX.058.","DOI":"10.15607\/RSS.2024.XX.058"},{"key":"e_1_3_2_55_2","unstructured":"A. Y. Ng D. Harada S. Russell \u201cPolicy invariance under reward transformations: Theory and application to reward shaping\u201d in Proceedings of the Sixteenth International Conference on Machine Learning (Morgan Kaufmann Publishers Inc. 1999) pp. 278\u2013287."},{"key":"e_1_3_2_56_2","unstructured":"S. Mysore G. Cheng Y. Zhao K. Saenko M. Wu \u201cMulti-critic actor learning: Teaching RL policies to act with style\u201d in International Conference on Learning Representations (OpenReview 2022); https:\/\/openreview.net\/forum?id=rJvY_5OzoI."},{"key":"e_1_3_2_57_2","unstructured":"F. Zargarbashi J. Cheng D. Kang R. Sumner S. Coros \u201cRobotKeyframing: Learning locomotion with high-level objectives via mixture of dense and sparse rewards\u201d in 8th Annual Conference on Robot Learning (OpenReview 2024); https:\/\/openreview.net\/forum?id=wcbrhPnOei."},{"key":"e_1_3_2_58_2","unstructured":"Z. Zhuang Z. Fu J. Wang C. Atkeson S. Schwertfeger C. Finn H. Zhao \u201cRobot parkour learning\u201d in 7th Annual Conference on Robot Learning (OpenReview 2023); https:\/\/openreview.net\/forum?id=uo937r5eTE."},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"e_1_3_2_60_2","doi-asserted-by":"crossref","unstructured":"H. Wang Z. Wang J. Ren Q. Ben T. Huang W. Zhang J. Pang \u201cBeamDojo: Learning agile humanoid locomotion on sparse footholds\u201d in Proceedings of Robotics: Science and Systems (RSS Foundation 2025) 10.15607\/RSS.2025.XXI.068.","DOI":"10.15607\/RSS.2025.XXI.068"},{"key":"e_1_3_2_61_2","unstructured":"A. Yu G. Yang R. Choi Y. Ravan J. Leonard P. Isola \u201cLearning visual parkour from generated images\u201d in 8th Annual Conference on Robot Learning (OpenReview 2024); https:\/\/openreview.net\/forum?id=cGswIOxHcN."},{"key":"e_1_3_2_62_2","unstructured":"G. Jocher A. Chaurasia J. Qiu Ultralytics YOLOv8 (2023); https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"e_1_3_2_63_2","unstructured":"Advanced Computing Center for the Arts and Design \u201cMoCap system and data\u201d; https:\/\/accad.osu.edu\/research\/motion-lab\/mocap-system-and-data."},{"key":"e_1_3_2_64_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201397","article-title":"Learning symmetric and low-energy locomotion","volume":"37","author":"Yu W.","year":"2018","unstructured":"W. Yu, G. Turk, C. K. Liu, Learning symmetric and low-energy locomotion. ACM Trans. Graph. 37, 1\u201312 (2018).","journal-title":"ACM Trans. Graph."},{"key":"e_1_3_2_65_2","doi-asserted-by":"crossref","unstructured":"T. He Z. Luo W. Xiao C. Zhang K. Kitani C. Liu G. Shi \u201cLearning human-to-humanoid real-time whole-body teleoperation\u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2024) pp. 8944\u20138951.","DOI":"10.1109\/IROS58592.2024.10801984"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.aed1152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T17:58:22Z","timestamp":1787162302000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.aed1152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":65,"journal-issue":{"issue":"117","published-print":{"date-parts":[[2026,8,19]]}},"alternative-id":["10.1126\/scirobotics.aed1152"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.aed1152","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]},"assertion":[{"value":"2025-10-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eaed1152"}}