{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:22:19Z","timestamp":1771924939483,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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","award":["62373344"],"award-info":[{"award-number":["62373344"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1109\/robio66223.2025.11377394","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:43:52Z","timestamp":1771879432000},"page":"2099-2104","source":"Crossref","is-referenced-by-count":0,"title":["VLC: A Human-Robot-Collaboration Framework with Vision-Language-Model"],"prefix":"10.1109","author":[{"given":"Zilong","family":"Chen","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lebin","family":"Liang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haonian","family":"Dong","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dehao","family":"Kong","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications,Nanjing,China,210023"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9677-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1108\/IR-11-2018-0231"},{"key":"ref3","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref4","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Conference on Robot Learning","author":"Zitkovich","year":"2023"},{"key":"ref5","author":"Ahn","year":"2022","journal-title":"Do as i can, not as i say: Grounding language in robotic affordances"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s42524-025-4136-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160906"},{"key":"ref9","author":"Driess","year":"2023","journal-title":"Palm-e: An embodied multimodal language model"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160591"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341846"},{"issue":"3","key":"ref12","first-page":"6","volume":"2","author":"Jiang","year":"2022","journal-title":"Vima: General robot manip-ulation with multimodal prompts"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.1997.646971"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IRDS.2002.1043874"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803320"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386040"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353496"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802194"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3016271"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918768950"}],"event":{"name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Chengdu, China","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,7]]}},"container-title":["2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373909\/11375854\/11377394.pdf?arnumber=11377394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:32:43Z","timestamp":1771921963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11377394\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/robio66223.2025.11377394","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}