{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:55:10Z","timestamp":1771923310248,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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":[[2025,12,3]]},"DOI":"10.1109\/robio66223.2025.11377338","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:43:52Z","timestamp":1771879432000},"page":"2354-2359","source":"Crossref","is-referenced-by-count":0,"title":["UAV-VLPA*: Vision-Language Guided Global-Local UAV Mission Planning from Satellite Imagery"],"prefix":"10.1109","author":[{"given":"Oleg","family":"Sautenkov","sequence":"first","affiliation":[{"name":"Grik Tadevosyan is with the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI),Abu Dhabi,United Arab Emirates"}]},{"given":"Aibek","family":"Akhmetkazy","sequence":"additional","affiliation":[{"name":"Grik Tadevosyan is with the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI),Abu Dhabi,United Arab Emirates"}]},{"given":"Yasheerah","family":"Yaqoot","sequence":"additional","affiliation":[{"name":"Grik Tadevosyan is with the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI),Abu Dhabi,United Arab Emirates"}]},{"given":"Muhammad Ahsan","family":"Mustafa","sequence":"additional","affiliation":[{"name":"Grik Tadevosyan is with the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI),Abu Dhabi,United Arab Emirates"}]},{"given":"Grik","family":"Tadevosyan","sequence":"additional","affiliation":[{"name":"Grik Tadevosyan is with the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI),Abu Dhabi,United Arab Emirates"}]},{"given":"Artem","family":"Lykov","sequence":"additional","affiliation":[{"name":"Grik Tadevosyan is with the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI),Abu Dhabi,United Arab Emirates"}]},{"given":"Valerii","family":"Serpiva","sequence":"additional","affiliation":[{"name":"Grik Tadevosyan is with the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI),Abu Dhabi,United Arab Emirates"}]},{"given":"Dzmitry","family":"Tsetserukou","sequence":"additional","affiliation":[{"name":"Grik Tadevosyan is with the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI),Abu Dhabi,United Arab Emirates"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.11.020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO64047.2024.10907428"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10974004"},{"key":"ref4","article-title":"CityNav: Language-goal aerial navigation dataset with geographic information","author":"Lee","year":"2024","journal-title":"arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00131"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.190"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10974117"},{"key":"ref8","volume-title":"Uav-codeagents: Scalable uav mission planning via multi-agent react and vision-language reasoning","author":"Sautenkov","year":"2025"},{"key":"ref9","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"arXiv"},{"key":"ref10","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":"ref11","article-title":"GPT-4 technical report","year":"2024","journal-title":"arXiv"},{"key":"ref12","article-title":"DeepSeek-VL: Towards real-world vision-language understanding","author":"Lu","year":"2024","journal-title":"arXiv"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01411"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ipsn61024.2024.00033"},{"key":"ref16","article-title":"Aerial vision-and-language navigation via semantic-topo-metric representation guided LLM reasoning","author":"Gao","year":"2024","journal-title":"arXiv"},{"key":"ref17","article-title":"Towards realistic UAV vision-language navigation: Platform, benchmark, and methodology","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref19","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv"},{"key":"ref20","article-title":"OpenVLA: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv"},{"key":"ref21","author":"Collaboration","year":"2024","journal-title":"Open x-embodiment: Robotic learning datasets and rt-x models"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831380"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA55743.2025.11128238","article-title":"Spine: Online semantic planning for missions with incomplete natural language specifications in unstructured environments","volume-title":"International Conference on Robotics and Automation (ICRA)","author":"Ravichandran","year":"2025"},{"key":"ref24","author":"De O. da Costa","year":"2020","journal-title":"Learning 2-opt heuristics for the traveling salesman problem via deep reinforcement learning"},{"key":"ref25","volume-title":"Molmo-7B-O BnB 4bit quantized 7GB","year":"2024"}],"event":{"name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Chengdu, China","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,7]]}},"container-title":["2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373909\/11375854\/11377338.pdf?arnumber=11377338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:50:51Z","timestamp":1771919451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11377338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/robio66223.2025.11377338","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}