{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:22:10Z","timestamp":1784136130231,"version":"3.55.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000935","name":"RSF","doi-asserted-by":"publisher","award":["24-41-02039"],"award-info":[{"award-number":["24-41-02039"]}],"id":[{"id":"10.13039\/100000935","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/iv64158.2025.11097824","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:54:55Z","timestamp":1754502895000},"page":"1195-1200","source":"Crossref","is-referenced-by-count":5,"title":["UAV-VLRR: Vision-Language Informed NMPC for Rapid Response in UAV Search and Rescue"],"prefix":"10.1109","author":[{"given":"Yasheerah","family":"Yaqoot","sequence":"first","affiliation":[{"name":"Skolkovo Institute of Science and Technology,Intelligent Space Robotics Laboratory, Center for Digital Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Ahsan","family":"Mustafa","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology,Intelligent Space Robotics Laboratory, Center for Digital Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oleg","family":"Sautenkov","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology,Intelligent Space Robotics Laboratory, Center for Digital Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Artem","family":"Lykov","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology,Intelligent Space Robotics Laboratory, Center for Digital Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valerii","family":"Serpiva","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology,Intelligent Space Robotics Laboratory, Center for Digital Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dzmitry","family":"Tsetserukou","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology,Intelligent Space Robotics Laboratory, Center for Digital Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/rs15133266"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.wem.2023.08.022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO64047.2024.10907428"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10974117"},{"key":"ref5","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"arXiv"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Int. Conf. on Machine Learning","author":"Radford","year":"2021"},{"key":"ref7","article-title":"GPT-4 technical report","year":"2024","journal-title":"arXiv"},{"key":"ref8","article-title":"Molmo and PixMo: Open weights and open data for state-of-the-art multimodal models","author":"Deitke","year":"2024","journal-title":"arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref10","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv"},{"key":"ref11","article-title":"UAV-VLPA*: A vision-language-path-action system for optimal route generation on a large scales","author":"Sautenkov","year":"2025","journal-title":"arXiv"},{"key":"ref12","article-title":"RaceVLA: VLA-based racing drone navigation with human-like behaviour","author":"Serpiva","year":"2025","journal-title":"arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3177279"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3173711"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3131690"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061307"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS57906.2023.10156232"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10974004"},{"key":"ref19","volume-title":"Molmo-7B-D BnB 4bit quantized 7GB","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-018-0139-4"}],"event":{"name":"2025 IEEE Intelligent Vehicles Symposium (IV)","location":"Cluj-Napoca, Romania","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11097351\/11097337\/11097824.pdf?arnumber=11097824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T05:07:30Z","timestamp":1754543250000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11097824\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iv64158.2025.11097824","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}