{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T03:21:42Z","timestamp":1779247302918,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"the Microsoft Corporation"},{"name":"Keio CMU partnership","award":["JP25KJ2068"],"award-info":[{"award-number":["JP25KJ2068"]}]},{"name":"Keio CMU partnership","award":["JSPS KAKENHI"],"award-info":[{"award-number":["JSPS KAKENHI"]}]},{"name":"Keio CMU partnership","award":["23K03478"],"award-info":[{"award-number":["23K03478"]}]},{"name":"JST Moonshot"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/lra.2026.3653281","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T23:58:44Z","timestamp":1768262324000},"page":"2706-2713","source":"Crossref","is-referenced-by-count":1,"title":["Affordance RAG: Hierarchical Multimodal Retrieval With Affordance-Aware Embodied Memory for Mobile Manipulation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0354-9070","authenticated-orcid":false,"given":"Ryosuke","family":"Korekata","sequence":"first","affiliation":[{"name":"Keio University, Yokohama, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9764-2189","authenticated-orcid":false,"given":"Quanting","family":"Xie","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2111-9081","authenticated-orcid":false,"given":"Yonatan","family":"Bisk","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0261-0510","authenticated-orcid":false,"given":"Komei","family":"Sugiura","sequence":"additional","affiliation":[{"name":"Keio University, Yokohama, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1975","article-title":"HomeRobot: Open-vocabulary mobile manipulation","volume-title":"Proc. CoRL","author":"Yenamandra","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.091"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127619"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"ref6","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342165"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3441495"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01612"},{"key":"ref11","article-title":"Embodied-RAG: General non-parametric embodied memory for retrieval and generation","author":"Xie","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/02783649251369549"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.442"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.050"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161534"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342093"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3522841"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2025.2469689"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01377"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref23","article-title":"RoboEXP: Action-conditioned scene graph via interactive exploration for robotic manipulation","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Jiang","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01470"},{"key":"ref25","article-title":"Toward general-purpose robots via foundation models: A survey and meta-analysis","author":"Hu","year":"2023"},{"key":"ref26","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Driess","year":"2023"},{"key":"ref27","first-page":"287","article-title":"Do as I Can, Not as I Say: Grounding language in robotic affordances","volume-title":"Proc. 6th Annu. Conf. Robot Learn.","author":"Brohan","year":"2023"},{"key":"ref28","article-title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4 V","author":"Yang","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref30","article-title":"GPT-4o: Optimized generative pre-trained transformer 4","year":"2024"},{"key":"ref31","first-page":"19769","article-title":"Segment everything everywhere all at once","volume-title":"Proc. 37th Int. Conf Neural Inf. Process. Syst.","author":"Zou","year":"2023"},{"key":"ref32","article-title":"text-embedding-3-large","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1561\/1500000016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811922"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2015.2448951"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2011.6106777"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11359420\/11345987.pdf?arnumber=11345987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T21:23:02Z","timestamp":1769203382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11345987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3653281","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}