{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:07:55Z","timestamp":1790269675663,"version":"4.1.0"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Dushi Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tro.2026.3721670","type":"journal-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:12:22Z","timestamp":1786389142000},"page":"3489-3512","source":"Crossref","is-referenced-by-count":2,"title":["HERMES: Human-to-Robot Embodied Learning From Multisource Motion Data for Mobile Dexterous Manipulation"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4919-9295","authenticated-orcid":false,"given":"Zhecheng","family":"Yuan","sequence":"first","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4081-0828","authenticated-orcid":false,"given":"Tianming","family":"Wei","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Langzhe","family":"Gu","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1301-7131","authenticated-orcid":false,"given":"Pu","family":"Hua","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhai","family":"Liang","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanpei","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8578-1261","authenticated-orcid":false,"given":"Huazhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3688078"},{"key":"ref2","first-page":"4269","article-title":"UniSkill: Imitating human videos via cross-embodiment skill representations","volume-title":"Proc. 9th Conf. Robot Learn. (CoRL)","author":"Kim","year":"2025"},{"key":"ref3","first-page":"816","article-title":"X-Sim: Cross-embodiment learning via real-to-sim-to-real","volume-title":"Proc. Conf. Robot Learn.","author":"Dan","year":"2025"},{"key":"ref4","first-page":"1","article-title":"MimicPlay: Long-horizon imitation learning by watching human play","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Wang","year":"2023"},{"key":"ref5","article-title":"Humanoid policy $\\sim$ human policy","author":"Qiu","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241227559"},{"key":"ref8","first-page":"654","article-title":"VideoDex: Learning dexterity from internet videos","volume-title":"Proc. Conf. Robot Learn.","author":"Shaw","year":"2023"},{"key":"ref9","first-page":"1","article-title":"Object-centric dexterous manipulation from human motion data","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Chen","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00656"},{"key":"ref11","article-title":"DexMachina: Functional retargeting for bimanual dexterous manipulation","author":"Mandi","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128180"},{"key":"ref13","first-page":"3809","article-title":"Sequential dexterity: Chaining dexterous policies for long-horizon manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Chen","year":"2023"},{"key":"ref14","first-page":"5220","article-title":"Twisting lids off with two hands","volume-title":"Proc. Conf. Robot Learn.","author":"Lin","year":"2025"},{"key":"ref15","first-page":"711","article-title":"ViNT: A foundation model for visual navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Shah","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref17","first-page":"651","article-title":"DexVIP: Learning dexterous grasping with human hand pose priors from video","volume-title":"Proc. Conf. Robot Learn.","author":"Mandikal","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3261745"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0070"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127989"},{"key":"ref22","article-title":"EgoDex: Learning dexterous manipulation from large-scale egocentric video","author":"Hoque","year":"2025"},{"key":"ref23","article-title":"DexTrack: Towards generalizable neural tracking control for dexterous manipulation from human references","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Liu","year":"2025"},{"key":"ref24","first-page":"73","article-title":"Robot parkour learning","volume-title":"Proc. Conf. Robot Learn.","author":"Zhuang","year":"2023"},{"key":"ref25","first-page":"1","article-title":"Humanoid Parkour learning","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Zhuang","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/02783649261455067"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01700"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.109"},{"key":"ref29","first-page":"1815","article-title":"Learning to manipulate anywhere: A visual generalizable framework for reinforcement learning","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Yuan","year":"2025"},{"key":"ref30","first-page":"1","article-title":"GenSim: Generating robotic simulation tasks via large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Wang","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3641152"},{"key":"ref32","first-page":"4926","article-title":"Sim-to-real reinforcement learning for vision-based dexterous manipulation on humanoids","volume-title":"Proc. Conf. Robot Learn.","author":"Lin","year":"2025"},{"key":"ref33","article-title":"GR00T N1: An open foundation model for generalist humanoid robots","author":"Bjorck","year":"2025"},{"key":"ref34","article-title":"DextrAH-RGB: Visuomotor policies to grasp anything with dexterous hands","author":"Singh","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128339"},{"key":"ref36","article-title":"RoboGSim: A Real2Sim2Real robotic Gaussian splatting simulator","author":"Li","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128407"},{"key":"ref39","first-page":"1","article-title":"DextrAH-G: Pixels-to-action dexterous arm-hand grasping with geometric fabrics","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Lum","year":"2024"},{"key":"ref40","first-page":"1975","article-title":"HomeRobot: Open-vocabulary mobile manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Yenamandra","year":"2023"},{"key":"ref41","first-page":"4066","article-title":"Mobile ALOHA: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","volume-title":"Proc. Conf. Robot Learn.","author":"Fu","year":"2025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00996"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.091"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127975"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref46","article-title":"Lang segment anything","author":"Medeiros","year":"2023"},{"key":"ref47","article-title":"GPT-4V(ision) system card","year":"2023"},{"key":"ref48","first-page":"1246","article-title":"Behavior robot suite: Streamlining real-world whole-body manipulation for everyday household activities","volume-title":"Proc. Conf. Robot Learn.","author":"Jiang","year":"2025"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3542323"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref51","article-title":"MuJoCoXLA (MJX)","year":"2023"},{"key":"ref52","article-title":"Mink: Python inverse kinematics based on MuJoCo","author":"Zakka","year":"2025"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00050"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01143"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.41"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"ref57","article-title":"Ar code","author":"Code","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197124"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01000"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.066"},{"key":"ref62","first-page":"794","article-title":"Visual imitation enables contextual humanoid control","volume-title":"Proc. Conf. Robot Learn.","author":"Allshire","year":"2025"},{"key":"ref63","first-page":"1","article-title":"DrM: Mastering visual reinforcement learning through dormant ratio minimization","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Xu","year":"2024"},{"key":"ref64","first-page":"32145","article-title":"The dormant neuron phenomenon in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sokar","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0946"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02047"},{"key":"ref72","volume-title":"RANSAC for Dummies","volume":"1","author":"Zuliani","year":"2009"},{"key":"ref73","volume-title":"Methods for Non-Linear Least Squares Problems","volume":"1","author":"Madsen","year":"2004"},{"key":"ref74","article-title":"Gauss-Newton\/Levenberg-Marquardt optimization","author":"Eade","year":"2013"},{"key":"ref75","volume-title":"Proportional-Integral-Derivative Control","volume":"6","author":"Willis","year":"1999"},{"key":"ref76","article-title":"FastTD3: Simple, fast, and capable reinforcement learning for humanoid control","author":"Seo","year":"2025"},{"key":"ref77","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref79","article-title":"Human-in-the-loop imitation learning using remote teleoperation","author":"Mandlekar","year":"2020"},{"key":"ref80","article-title":"RaC: Robot learning for long-horizon tasks by scaling recovery and correction","author":"Hu","year":"2025"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2026.3709635"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21831"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.3390\/s19102251"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00193"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32330"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref90","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Dosovitskiy","year":"2021"},{"key":"ref91","article-title":"TensorRT: NVIDIAs SDK for high-performance deep learning inference","year":"2025"},{"key":"ref92","article-title":"Urdf studio","year":"2026"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8860\/11297026\/11646888.pdf?arnumber=11646888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:45:21Z","timestamp":1790268321000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11646888\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/tro.2026.3721670","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}