{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T17:32:30Z","timestamp":1784914350651,"version":"3.55.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Samsung Research America LEAP-U Program"},{"name":"Industrial Technology Innovation Program","award":["P0028404"],"award-info":[{"award-number":["P0028404"]}]},{"name":"Ministry of Industry, Trade and Energy of Korea"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/lra.2026.3653320","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:41:16Z","timestamp":1768423276000},"page":"3087-3094","source":"Crossref","is-referenced-by-count":2,"title":["EMMA: Scaling Mobile Manipulation via Egocentric Human Data"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5360-3510","authenticated-orcid":false,"given":"Lawrence Y.","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pranav","family":"Kuppili","sequence":"additional","affiliation":[{"name":"School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan","family":"Punamiya","sequence":"additional","affiliation":[{"name":"School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patcharapong","family":"Aphiwetsa","sequence":"additional","affiliation":[{"name":"School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhruv","family":"Patel","sequence":"additional","affiliation":[{"name":"School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simar","family":"Kareer","sequence":"additional","affiliation":[{"name":"School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1972-328X","authenticated-orcid":false,"given":"Sehoon","family":"Ha","sequence":"additional","affiliation":[{"name":"School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8744-3861","authenticated-orcid":false,"given":"Danfei","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127989"},{"key":"ref3","article-title":"Humanoid policy human policy","author":"Qiu","year":"2025"},{"key":"ref4","first-page":"892","article-title":"R3M: A universal visual representation for robot manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Nair","year":"2023"},{"key":"ref5","first-page":"201","article-title":"MimicPlay: Long-horizon imitation learning by watching human play","volume-title":"Proc. Conf. Robot Learn.","author":"Wang","year":"2023"},{"key":"ref6","first-page":"2475","article-title":"Flow as the cross-domain manipulation interface","volume-title":"Proc. Conf. Robot Learn.","author":"Xu","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.092"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_18"},{"key":"ref9","article-title":"Project Aria: A new tool for egocentric multi-modal AI research","author":"Engel","year":"2023"},{"key":"ref10","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Brohan","year":"2023"},{"key":"ref11","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Conf. Robot Learn.","author":"Kim","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref15","first-page":"6892","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","volume-title":"Proc. IEEE Int. Conf. Robot. Autom.","author":"ONeill","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref17","first-page":"308","article-title":"Fully autonomous real-world reinforcement learning with applications to mobile manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Sun","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160934"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref20","article-title":"SkillBlender: Towards versatile humanoid whole-body loco-manipulation via skill blending","author":"Kuang","year":"2025"},{"key":"ref21","article-title":"Multi-skill mobile manipulation for object rearrangement","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3336109"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561315"},{"key":"ref24","article-title":"Adaptive mobile manipulation for articulated objects in the open world","author":"Xiong","year":"2024"},{"key":"ref25","first-page":"138","article-title":"Deep whole-body control: Learning a unified policy for manipulation and locomotion","volume-title":"Proc. Conf. Robot Learn.","author":"Fu","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802201"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.049"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3620620"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.070"},{"key":"ref30","first-page":"1643","article-title":"Hypermotion: Learning hybrid behavior planning for autonomous loco-manipulation","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Wang","year":"2024"},{"key":"ref31","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn.","author":"Ahn","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt1ffjjxf.10"},{"key":"ref34","first-page":"17","article-title":"$\\pi _{0.5}$: A vision-language-action model with open-world generalization","volume-title":"Proc. Conf. Robot Learn.","author":"Intelligence","year":"2025"},{"key":"ref35","first-page":"3397","article-title":"Open-world object manipulation using pre-trained vision-language models","volume-title":"Proc. Conf. Robot Learn.","author":"Stone","year":"2023"},{"key":"ref36","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":"ref37","first-page":"2828","article-title":"Humanplus: Humanoid shadowing and imitation from humans","volume-title":"Proc. Conf. Robot Learn.","author":"Fu","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128717"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128652"},{"issue":"3","key":"ref40","first-page":"535","article-title":"Team JANUS humanoid avatar: A cybernetic avatar to embody human telepresence","volume-title":"Proc. RSS Workshop","volume":"17","author":"Cisneros","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adh3834"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids43949.2019.9035059"},{"key":"ref43","first-page":"1367","article-title":"Error-aware imitation learning from teleoperation data for mobile manipulation","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Wong","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342371"},{"key":"ref45","first-page":"4545","article-title":"Phantom: Training robots without robots using only human videos","volume-title":"Proc. Conf. Robot Learn.","author":"Lepert","year":"2025"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128834"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375150"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812316"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"ref50","first-page":"617","article-title":"Learning navigation subroutines from egocentric videos","volume-title":"Proc. Conf. Robot Learn.","author":"Kumar","year":"2019"},{"key":"ref51","first-page":"124420","article-title":"Scaling proprioceptive-visual learning with heterogeneous pre-trained transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2024"},{"key":"ref52","article-title":"Project Aria: A new tool for egocentric multi-modal AI research","author":"Engel","year":"2023"},{"key":"ref53","article-title":"RDT-1B: A diffusion foundation model for bimanual manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11359420\/11352854.pdf?arnumber=11352854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:26:14Z","timestamp":1769721974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11352854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":54,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3653320","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}