{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:19:29Z","timestamp":1783401569058,"version":"3.54.6"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":["62325405"],"award-info":[{"award-number":["62325405"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University Initiative Scientific Research Program"},{"name":"Tsinghua-Efort Joint Research Center for EAI Computation and Perception and SunRisingAI Lab"},{"name":"Beijing National Research Center for Information Science, Technology"},{"name":"Beijing Innovation Center for Future Chips"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/lra.2026.3706941","type":"journal-article","created":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:51:30Z","timestamp":1782330690000},"page":"9771-9778","source":"Crossref","is-referenced-by-count":0,"title":["Appliances Describe Themselves: Part\u2013Function\u2013State Modeling for Appliance Manipulation Planning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9230-8355","authenticated-orcid":false,"given":"Xinting","family":"Yang","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3831-3845","authenticated-orcid":false,"given":"Jincheng","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4490-2896","authenticated-orcid":false,"given":"Qiuyi","family":"Gu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4705-3814","authenticated-orcid":false,"given":"Jiahao","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6108-5157","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0597-4512","authenticated-orcid":false,"given":"Wenbo","family":"Ding","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00910"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127525"},{"key":"ref4","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":"Brohan","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00674"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128705"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.262"},{"key":"ref10","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref13","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. Conf. Robot Learn.","author":"Huang","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801352"},{"key":"ref15","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Zitkovich","year":"2023"},{"key":"ref16","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Driess","year":"2023"},{"key":"ref17","article-title":"CogACT: A foundational vision-language-action model for synergizing cognition and action in robotic manipulation","author":"Li","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611112"},{"key":"ref19","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V","author":"Yang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"ref21","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01377"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02104"},{"key":"ref26","article-title":"Robot operation of home appliances by reading user manuals","volume-title":"Proc. Conf. Robot Learn.","author":"Zhang","year":"2025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref28","article-title":"Ultralytics yolov8","author":"Jocher","year":"2023"},{"key":"ref29","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024"},{"key":"ref30","article-title":"GPT-4o system card","year":"2024"},{"key":"ref31","article-title":"Introducing claude 4.5 sonnet","year":"2025"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11570239\/11576562.pdf?arnumber=11576562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:06:27Z","timestamp":1783400787000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11576562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":31,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3706941","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}