{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:11:30Z","timestamp":1765519890736,"version":"3.48.0"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246192","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"13544-13551","source":"Crossref","is-referenced-by-count":0,"title":["RwoR: Generating Robot Demonstrations from Human Hand Collection for Policy Learning without Robot"],"prefix":"10.1109","author":[{"given":"Liang","family":"Heng","sequence":"first","affiliation":[{"name":"Peking University,CFCS, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqi","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University,CFCS, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangqing","family":"Mao","sequence":"additional","affiliation":[{"name":"Peking University,CFCS, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaming","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of Multimedia Information Processing, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruolin","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of Multimedia Information Processing, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingli","family":"Wei","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of Multimedia Information Processing, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of Multimedia Information Processing, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueru","family":"Jia","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of Multimedia Information Processing, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Gu","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of Multimedia Information Processing, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent Robotics X Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanghang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of Multimedia Information Processing, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Dong","sequence":"additional","affiliation":[{"name":"Peking University,CFCS, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"article-title":"Act3d: 3d feature field transformers for multi-task robotic manipulation","volume-title":"7th Annual Conference on Robot Learning","author":"Gervet","key":"ref2"},{"key":"ref3","first-page":"785","article-title":"Perceiver-actor: A multitask transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"7th Annual Conference on Robot Learning","author":"Zitkovich","key":"ref4"},{"journal-title":"Lift3d foundation policy: Lifting 2d large-scale pretrained models for robust 3d robotic manipulation","year":"2024","author":"Jia","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127295"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801581"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160547"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128717"},{"journal-title":"Ar2-d2: Training a robot without a robot","year":"2023","author":"Duan","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.045"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.043"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812402"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref19","article-title":"Learning from active human involvement through proxy value propagation","volume":"36","author":"Peng","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801993"},{"journal-title":"Robomamba: Multimodal state space model for efficient robot reasoning and manipulation","year":"2024","author":"Liu","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02574"},{"journal-title":"Hybridvla: Collaborative diffusion and autoregression in a unified vision-language-action model","year":"2025","author":"Liu","key":"ref24"},{"journal-title":"Fast-in-slow: A dual-system foundation model unifying fast manipulation within slow reasoning","year":"2025","author":"Chen","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3477095"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128671"},{"article-title":"Autonomous interactive correction mllm for robust robotic manipulation","volume-title":"8th Annual Conference on Robot Learning","author":"Xiong","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10801581"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.013"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128180"},{"journal-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","year":"2024","author":"Fu","key":"ref34"},{"journal-title":"Omnih2o: Universal and dexterous human-to-humanoid whole-body teleoperation and learning","year":"2024","author":"He","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769593"},{"key":"ref37","first-page":"371","article-title":"A comparison of remote robot teleoperation interfaces for general object manipulation","volume-title":"Proceedings of the 2017 ACM\/IEEE international conference on human-robot interaction","author":"Kent"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157691"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989046"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2012.6343868"},{"key":"ref41","first-page":"879","article-title":"Roboturk: A crowdsourcing platform for robotic skill learning through imitation","volume-title":"Conference on Robot Learning","author":"Mandlekar"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28619-4_28"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2737046"},{"key":"ref45","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International conference on machine learning","author":"Jaegle"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.010"},{"journal-title":"Cacti: A framework for scalable multi-task multi-scene visual imitation learning","year":"2022","author":"Mandi","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160761"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.069"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00190"},{"journal-title":"Sam 2: Segment anything in images and videos","year":"2024","author":"Ravi","key":"ref55"},{"journal-title":"Inpaint anything: Segment anything meets image inpainting","year":"2023","author":"Yu","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246192.pdf?arnumber=11246192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:10:10Z","timestamp":1765519810000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246192","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}