{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:28:18Z","timestamp":1787016498073,"version":"build-2736575974"},"reference-count":52,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"102","content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2025,5,28]]},"abstract":"<jats:p>Coordinating the motion between lower and upper limbs and aligning limb control with perception are substantial challenges in robotics, particularly in dynamic environments. To this end, we introduce an approach for enabling legged mobile manipulators to play badminton, a task that requires precise coordination of perception, locomotion, and arm swinging. We propose a unified reinforcement learning\u2013based control policy for whole-body visuomotor skills involving all degrees of freedom to achieve effective shuttlecock tracking and striking. This policy is informed by a perception noise model that uses real-world camera data, allowing for consistent perception error levels between simulation and deployment and encouraging learned active perception behaviors. Our method includes a shuttlecock prediction model and constrained reinforcement learning for robust motion control to enhance deployment readiness. Extensive experimental results in a variety of environments validate the robot\u2019s capability to predict shuttlecock trajectories, navigate the service area effectively, and execute precise strikes against human players, demonstrating the feasibility of using legged mobile manipulators in complex and dynamic sports scenarios.<\/jats:p>","DOI":"10.1126\/scirobotics.adu3922","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T13:58:11Z","timestamp":1748440691000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":24,"title":["Learning coordinated badminton skills for legged manipulators"],"prefix":"10.1126","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8574-4978","authenticated-orcid":true,"given":"Yuntao","family":"Ma","sequence":"first","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, 8092 Zurich, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9301-0253","authenticated-orcid":true,"given":"Andrei","family":"Cramariuc","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, 8092 Zurich, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farbod","family":"Farshidian","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, 8092 Zurich, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-4990","authenticated-orcid":true,"given":"Marco","family":"Hutter","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zurich, 8092 Zurich, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"M. H. Raibert Legged Robots That Balance (MIT Press 1986).","DOI":"10.1109\/MEX.1986.4307016"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3351554"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"B. Katz J. Di Carlo S. Kim \u201cMini Cheetah: A platform for pushing the limits of dynamic quadruped control \u201d in IEEE International Conference on Robotics and Automation (IEEE 2019) pp. 6295\u20136301.","DOI":"10.1109\/ICRA.2019.8793865"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3386391"},{"key":"e_1_3_2_6_2","doi-asserted-by":"crossref","unstructured":"J.-R. Chiu J.-P. Sleiman M. Mittal F. Farshidian M. Hutter \u201cA collision-free MPC for whole-body dynamic locomotion and manipulation \u201d in IEEE International Conference on Robotics and Automation (IEEE 2022) pp. 4686\u20134693.","DOI":"10.1109\/ICRA46639.2022.9812280"},{"key":"e_1_3_2_7_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 (IEEE 2023) pp. 12205\u201312211.","DOI":"10.1109\/ICRA48891.2023.10160436"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151396"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231224053"},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"T. He C. Zhang W. Xiao G. He C. Liu G. Shi \u201cAgile but safe: Learning collision-free high-speed legged locomotion \u201d in Robotics: Science and Systems XX D. Kulic G. Venture K. Bekris E. Coronado Eds. (RSS Foundation 2024).","DOI":"10.15607\/RSS.2024.XX.059"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"X. Cheng K. Shi A. Agarwal D. Pathak \u201cExtreme parkour with legged robots \u201d in IEEE International Conference on Robotics and Automation (IEEE 2024) pp. 11443\u201311450.","DOI":"10.1109\/ICRA57147.2024.10610200"},{"key":"e_1_3_2_13_2","unstructured":"Z. Zhuang Z. Fu J. Wang C. Atkeson S. Schwertfeger C. Finn H. Zhao \u201cRobot parkour learning \u201d in Proceedings of the 7th Conference on Robot Learning J. Tan M. Toussant K. Darvish Eds. (PMLRPress 2023) pp. 73\u201392."},{"key":"e_1_3_2_14_2","unstructured":"K. Caluwaerts A. Iscen J. C. Kew W. Yu T. Zhang D. Freeman K.-H. Lee L. Lee S. Saliceti V. Zhuang N. Batchelor S. Bohez F. Casarini J. E. Chen O. Cortes E. Coumans A. Dostmohamed G. Dulac-Arnold A. Escontrela E. Frey R. Hafner D. Jain B. Jyenis Y. Kuang E. Lee L. Luu O. Nachum K. Oslund J. Powell D. Reyes F. Romano F. Sadeghi R. Sloat B. Tabanpour D. Zheng M. Neunert R. Hadsell N. Heess F. Nori J. Seto C. Parada V. Sindhwani V. Vanhoucke J. Tan Barkour: Benchmarking animal-level agility with quadruped robots. arXiv:2305.14654 [cs.RO] (2023)."},{"key":"e_1_3_2_15_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 (IEEE 2023) pp. 5155\u20135162.","DOI":"10.1109\/ICRA48891.2023.10160325"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8022"},{"key":"e_1_3_2_17_2","unstructured":"D. B. D\u2019Ambrosio S. Abeyruwan L. Graesser A. Iscen H. B. Amor A. Bewley B. J. Reed K. Reymann L. Takayama Y. Tassa K. Choromanski E. Coumans D. Jain N. Jaitly N. Jaques S. Kataoka Y. Kuang N. Lazic R. Mahjourian S. Q. Moore K. Oslund A. Shankar V. Sindhwani V. Vanhoucke G. Vesom P. Xu P. R. Sanketi Achieving human level competitive robot table tennis. arXiv:2408.03906 [cs.RO] (2024)."},{"key":"e_1_3_2_18_2","doi-asserted-by":"crossref","unstructured":"T. Ding L. Graesser S. Abeyruwan D. B. D\u2019Ambrosio A. Shankar P. Sermanet P. R. Sanketi C. Lynch \u201cLearning high speed precision table tennis on a physical robot \u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IEEE 2022) pp. 10780\u201310787.","DOI":"10.1109\/IROS47612.2022.9982205"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10140-6"},{"key":"e_1_3_2_20_2","unstructured":"S. W. Abeyruwan L. Graesser D. B. D\u2019Ambrosio A. Singh A. Shankar A. Bewley D. Jain K. M. Choromanski P. R. Sanketi \u201ci-sim2real: Reinforcement learning of robotic policies in tight human-robot interaction loops \u201d in Proceedings of the 6th Conference on Robot Learning K. Liu D. Kulic J. Ichnowski Eds. (PMLRPress 2023) pp. 212\u2013224."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10146-0"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"S. Zimmermann R. Poranne S. Coros \u201cGo fetch! Dynamic grasps using Boston Dynamics Spot with external robotic arm \u201d in IEEE International Conference on Robotics and Automation (IEEE 2021) pp. 4488\u20134494.","DOI":"10.1109\/ICRA48506.2021.9561835"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143567"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068908"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3336109"},{"key":"e_1_3_2_26_2","unstructured":"M. Liu Z. Chen X. Cheng Y. Ji R. Qiu R. Yang X. Wang \u201cVisual whole-body control for legged loco-manipulation \u201d in Proceedings of the 8th Conference on Robot Learning P. Agrawal O. Kroemer W. Burgard Eds. (PMLRPress 2024) pp. 234\u2013257."},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"J. Dao H. Duan A. Fern \u201cSim-to-real learning for humanoid box loco-manipulation \u201d in IEEE International Conference on Robotics and Automation (IEEE 2024) pp. 16930\u201316936.","DOI":"10.1109\/ICRA57147.2024.10610977"},{"key":"e_1_3_2_28_2","unstructured":"Z. Fu X. Cheng D. Pathak \u201cDeep whole-body control: Learning a unified policy for manipulation and locomotion \u201d in Proceedings of the 6th Conference on Robot Learning K. Liu D. Kulic J. Ichnowski Eds. (PMLRPress 2023) pp. 138\u2013149."},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Y. Ma F. Farshidian M. Hutter \u201cLearning arm-assisted fall damage reduction and recovery for legged mobile manipulators \u201d in IEEE International Conference on Robotics and Automation (IEEE 2023) pp. 12149\u201312155.","DOI":"10.1109\/ICRA48891.2023.10160582"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"e_1_3_2_31_2","unstructured":"Z. Fu Q. Zhao Q. Wu G. Wetzstein C. Finn \u201cHumanPlus: Humanoid Shadowing and imitation from humans \u201d in Proceedings of the 8th Conference on Robot Learning P. Agrawal O. Kroemer W. Burgard Eds. (PMLRPress 2024) pp. 2828\u20132844."},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"X. Cheng Y. Ji J. Chen R. Yang X. Wang Expressive whole-body control for humanoid robots. arXiv:2402.16796 [cs.RO] (2024).","DOI":"10.15607\/RSS.2024.XX.107"},{"key":"e_1_3_2_33_2","unstructured":"H. Ha Y. Gao Z. Fu J. Tan S. Song UMI on legs: Making manipulation policies mobile with manipulation-centric whole-body controllers. arXiv:2407.10353 [cs.RO] (2024)."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"e_1_3_2_36_2","unstructured":"A. Agarwal A. Kumar J. Malik D. Pathak \u201cLegged locomotion in challenging terrains using egocentric vision \u201d in Proceedings of the 6th Conference on Robot Learning K. Liu D. Kulic J. Ichnowski Eds. (PMLRPress 2023) pp. 403\u2013415."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184779"},{"key":"e_1_3_2_38_2","unstructured":"C. Schwarke V. Klemm M. Van der Boon M. Bjelonic M. Hutter \u201cCuriosity-driven learning of joint locomotion and manipulation tasks \u201d in Proceedings of the 7th Conference on Robot Learning J. Tan M. Toussant K. Darvish Eds. (PMLRPress 2023) pp. 2594\u20132610."},{"key":"e_1_3_2_39_2","unstructured":"Open-Ended Learning Team A. Stooke A. Mahajan C. Barros C. Deck J. Bauer J. Sygnowski M. Trebacz M. Jaderberg M. Mathieu N. McAleese N. Bradley-Schmieg N. Wong N. Porcel R. Raileanu S. Hughes-Fitt V. Dalibard W. M. Czarnecki Open-ended learning leads to generally capable agents. arXiv:2107.12808 [cs.LG] (2021)."},{"key":"e_1_3_2_40_2","doi-asserted-by":"crossref","unstructured":"N. Rudin D. Hoeller M. Bjelonic M. Hutter \u201cAdvanced skills by learning locomotion and local navigation end-to-end \u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IEEE 2022) pp. 2497\u20132503.","DOI":"10.1109\/IROS47612.2022.9981198"},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"L. Pinto M. Andrychowicz P. Welinder W. Zaremba P. Abbeel \u201cAsymmetric actor critic for image-based robot learning \u201d in Robotics: Science and Systems XIV (RSS Foundation 2018).","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/17\/6\/063001"},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","unstructured":"J. Lee L. Schroth V. Klemm M. Bjelonic A. Reske M. Hutter Evaluation of constrained reinforcement learning algorithms for legged locomotion. arXiv:2309.15430 [cs.RO] (2023).","DOI":"10.1109\/IROS58592.2024.10801341"},{"key":"e_1_3_2_44_2","doi-asserted-by":"crossref","unstructured":"S. Khattak H. Nguyen F. Mascarich T. Dang K. Alexis \u201cComplementary multi\u2013modal sensor fusion for resilient robot pose estimation in subterranean environments \u201d in International Conference on Unmanned Aircraft Systems (IEEE 2020) pp. 1024\u20131029.","DOI":"10.1109\/ICUAS48674.2020.9213865"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"S. Lynen M. W. Achtelik S. Weiss M. Chli R. Siegwart \u201cA robust and modular multi-sensor fusion approach applied to MAV navigation \u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IEEE 2013) pp. 3923\u20133929.","DOI":"10.1109\/IROS.2013.6696917"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","unstructured":"J. Tan T. Zhang E. Coumans A. Iscen Y. Bai D. Hafner S. Bohez V. Vanhoucke Sim-to-real: Learning agile locomotion for quadruped robots. arXiv:1804.10332 [cs.RO] (2018).","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","unstructured":"M. Hutter C. Gehring D. Jud A. Lauber C. D. Bellicoso V. Tsounis J. Hwangbo K. Bodie P. Fankhauser M. Bloesch R. Diethelm S. Bachmann A. Melzer M. Hoepflinger \u201cANYmal\u2014A highly mobile and dynamic quadrupedal robot \u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IEEE 2016) pp. 38\u201344.","DOI":"10.1109\/IROS.2016.7758092"},{"key":"e_1_3_2_49_2","unstructured":"V. Makoviychuk L. Wawrzyniak Y. Guo M. Lu K. Storey M. Macklin D. Hoeller N. Rudin A. Allshire A. Handa G. State \u201cIsaac Gym: High performance GPU based physics simulation for robot learning \u201d in Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks J. Vanschoren S. Yeung Eds. (NeurIPS 2021)."},{"key":"e_1_3_2_50_2","unstructured":"N. Rudin D. Hoeller P. Reist M. Hutter \u201cLearning to walk in minutes using massively parallel deep reinforcement learning \u201d in Proceedings of the 5th Conference on Robot Learning A. Faust D. Hsu G. Neumann Eds. (PMLRPress 2022) pp. 91\u2013100."},{"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","unstructured":"G. Bradski \u201cThe OpenCV Library \u201d Dr. Dobb's Journal of Software Tools 8 November 2000."},{"key":"e_1_3_2_53_2","unstructured":"M. Andrychowicz A. Raichuk P. Sta\u0144czyk M. Orsini S. Girgin R. Marinier L. Hussenot M. Geist O. Pietquin M. Michalski S. Gelly O. Bachem What matters in on-policy reinforcement learning? A large-scale empirical study paper presented at ICLR 2021: The Ninth International Conference on Learning Representations Vienna Austria 3 to 7 May 2021 (virtual)."}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.adu3922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T13:58:18Z","timestamp":1748440698000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.adu3922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,28]]},"references-count":52,"journal-issue":{"issue":"102","published-print":{"date-parts":[[2025,5,28]]}},"alternative-id":["10.1126\/scirobotics.adu3922"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.adu3922","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,28]]},"assertion":[{"value":"2024-11-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eadu3922"}}