{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T23:28:32Z","timestamp":1771889312160,"version":"3.50.1"},"reference-count":35,"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"}]},{"DOI":"10.13039\/501100005089","name":"Beijing Municipal Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005089","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\/iros60139.2025.11246003","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"4480-4487","source":"Crossref","is-referenced-by-count":4,"title":["IDAGC: Adaptive Generalized Human-Robot Collaboration via Human Intent Estimation and Multimodal Policy Learning"],"prefix":"10.1109","author":[{"given":"Haotian","family":"Liu","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,CAS Engineering Laboratory for Intelligent Industrial Vision, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchuang","family":"Tong","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,CAS Engineering Laboratory for Intelligent Industrial Vision, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanchen","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,CAS Engineering Laboratory for Intelligent Industrial Vision, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaojie","family":"Ju","sequence":"additional","affiliation":[{"name":"Zhejiang University,Key Laboratory for Biomedical Engineering of Ministry of Education,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengtao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,CAS Engineering Laboratory for Intelligent Industrial Vision, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281483"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2024.124512"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3107357"},{"key":"ref4","first-page":"12 956","article-title":"Towards proactive safe human-robot collaborations via data-efficient conditional behavior prediction","volume-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","author":"Ravi"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3430131"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3307006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3330226"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611293"},{"key":"ref9","article-title":"Openvla: An open-source vision-language-action model","volume-title":"Proceedings of the 8th conference on robot learning","author":"Kim"},{"key":"ref10","article-title":"Extract: Efficient policy learning by extracting transferable robot skills from offline data","volume-title":"Proceedings of the 8th conference on robot learning","author":"Zhang"},{"key":"ref11","article-title":"Modem: accelerating visual model-based reinforcement learning with demonstrations","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hansen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4484"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2946721"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3370025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.028"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2025.3577296"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3266378"},{"key":"ref19","article-title":"Shared navigational control and user intent detection in an intelligent walker","volume-title":"AAAI Fall Symposium: Caring Machines","author":"Huang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2014.6943678"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3106543"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611507"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127335"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3228443"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref26","first-page":"785","article-title":"Perceiver-actor: a multi-task transformer for robotic manipulation","volume-title":"Proceedings of The 6th Conference on Robot Learning","volume":"205","author":"Shridhar"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128452"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","first-page":"5776","article-title":"Minilm: deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume-title":"Advances in neural information processing systems","volume":"33","author":"Wang","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610040"},{"key":"ref35","first-page":"44 776","article-title":"Libero: benchmarking knowledge transfer for lifelong robot learning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"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\/11246003.pdf?arnumber=11246003","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:35:45Z","timestamp":1766061345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246003\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246003","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}