{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T02:56:33Z","timestamp":1771556193389,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"EPSRC Impact Acceleration Account (IAA) “Robotics Inversion"},{"name":"Future Artificial Intelligence Research"},{"name":"European Union Next-GenerationEU"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/lra.2025.3606790","type":"journal-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T18:23:20Z","timestamp":1757010200000},"page":"11267-11274","source":"Crossref","is-referenced-by-count":2,"title":["Select2Plan: Training-Free ICL-Based Planning Through VQA and Memory Retrieval"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9782-6451","authenticated-orcid":false,"given":"Davide","family":"Buoso","sequence":"first","affiliation":[{"name":"VANDAL Lab, Politecnico di Torino, Torino, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luke","family":"Robinson","sequence":"additional","affiliation":[{"name":"Mobile Robotics Group, University of Oxford, Oxford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1212-3465","authenticated-orcid":false,"given":"Giuseppe","family":"Averta","sequence":"additional","affiliation":[{"name":"VANDAL Lab, Politecnico di Torino, Torino, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0259-5732","authenticated-orcid":false,"given":"Philip","family":"Torr","sequence":"additional","affiliation":[{"name":"Torr Vision Group, University of Oxford, Oxford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Franzmeyer","sequence":"additional","affiliation":[{"name":"Torr Vision Group, University of Oxford, Oxford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-5839","authenticated-orcid":false,"given":"Daniele De","family":"Martini","sequence":"additional","affiliation":[{"name":"Mobile Robotics Group, University of Oxford, Oxford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3034524"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SWC50871.2021.00027"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"ref4","article-title":"Perceive, reflect, and plan: Designing LLM agent for goal-directed city navigation without instructions","author":"Zeng","year":"2024"},{"issue":"8","key":"ref5","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610398"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3401020"},{"issue":"2","key":"ref8","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"1","author":"Hu","year":"2023"},{"key":"ref9","first-page":"37321","article-title":"PIVOT: Iterative visual prompting elicits actionable knowledge for VLMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nasiriany","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802716"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63596-0_12"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341260"},{"key":"ref13","article-title":"NeRFoot: Robot-footprint estimation for image-based visual servoing","author":"Zhong","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812027"},{"key":"ref15","first-page":"711","article-title":"ViNT: A foundation model for visual navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Shah","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref17","article-title":"Visual semantic navigation using scene priors","author":"Yang","year":"2018"},{"key":"ref18","article-title":"VTNet: Visual transformer network for object goal navigation","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Du","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3368696"},{"key":"ref20","first-page":"492","article-title":"LM-NAV: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. Conf. Robot Learn.","author":"Shah","year":"2023"},{"key":"ref21","first-page":"5326","article-title":"Manipulate-anything: Automating real-world robots using vision-language models","volume-title":"Proc. Conf. Robot Learn.","volume":"270","author":"Duan","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.096"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291025"},{"key":"ref26","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"Kolve","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2015.2411627"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2961052"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref30","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Reid","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00691"},{"key":"ref32","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wei"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11169302\/11151762.pdf?arnumber=11151762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:03:07Z","timestamp":1759237387000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11151762\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":32,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3606790","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}