{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:15:58Z","timestamp":1765520158459,"version":"3.48.0"},"reference-count":37,"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\/iros60139.2025.11246581","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"842-849","source":"Crossref","is-referenced-by-count":0,"title":["TagGuideBot: Enhancing Robot Intelligence with Object Tags and VLMs"],"prefix":"10.1109","author":[{"given":"Jiayi","family":"Chen","sequence":"first","affiliation":[{"name":"Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"He","sequence":"additional","affiliation":[{"name":"Shenzhen University,College of Computer Science and Software Engineering,P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"F. Richard","family":"Yu","sequence":"additional","affiliation":[{"name":"Carleton University,School of Information Technology,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"694","article-title":"Rvt: Robotic view transformer for 3d object manipulation","volume-title":"Processings of the Conference on Robot Learning","author":"Goyal"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802366"},{"article-title":"Act3d: 3d feature field transformers for multi-task robotic manipulation","volume-title":"Proceedings of the 7th Annual Conference on Robot Learning","author":"Gervet","key":"ref3"},{"article-title":"3d diffuser actor: Policy diffusion with 3d scene representations","year":"2024","author":"Ke","key":"ref4"},{"key":"ref5","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Proceedings of the Conference on Robot Learning","author":"Brohan"},{"article-title":"Palm-e: An embodied multimodal language model","year":"2023","author":"Driess","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","year":"2023","author":"Huang","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3441495"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342363"},{"article-title":"Llm as a robotic brain: Unifying egocentric memory and control","year":"2023","author":"Mai","key":"ref12"},{"article-title":"Large language models as commonsense knowledge for large-scale task planning","year":"2023","author":"Zhao","key":"ref13"},{"article-title":"Large language models as generalizable policies for embodied tasks","year":"2023","author":"Szot","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"article-title":"Instruct2act: Mapping multi-modality instructions to robotic actions with large language model","year":"2023","author":"Huang","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00110"},{"issue":"3","key":"ref23","first-page":"6","article-title":"Vima: General robot manipulation with multimodal prompts","volume":"2","author":"Jiang","year":"2022"},{"article-title":"Open-world object manipulation using pre-trained vision-language models","year":"2023","author":"Stone","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref26"},{"key":"ref27","first-page":"785","article-title":"Perceiver-actor: A multitask transformer for robotic manipulation","volume-title":"Processings of the Conference on Robot Learning","author":"Shridhar"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.055"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2013.6696520"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref35"},{"article-title":"Visualrwkv: Exploring recurrent neural networks for visual language models","year":"2024","author":"Hou","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"}],"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\/11246581.pdf?arnumber=11246581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:12:20Z","timestamp":1765519940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246581","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}