{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:09:42Z","timestamp":1785856182630,"version":"3.56.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:00:00Z","timestamp":1756771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:00:00Z","timestamp":1756771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,2]]},"DOI":"10.1109\/ecmr65884.2025.11163198","type":"proceedings-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T17:43:37Z","timestamp":1758217417000},"page":"1-6","source":"Crossref","is-referenced-by-count":15,"title":["UAV-VLN: End-to-End Vision Language guided Navigation for UAVs"],"prefix":"10.1109","author":[{"given":"Pranav","family":"Saxena","sequence":"first","affiliation":[{"name":"Birla Institute of Technology and Science Pilani,Goa,India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nishant","family":"Raghuvanshi","sequence":"additional","affiliation":[{"name":"Birla Institute of Technology and Science Pilani,Goa,India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neena","family":"Goveas","sequence":"additional","affiliation":[{"name":"Birla Institute of Technology and Science Pilani,Goa,India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Spring48590.2020.9129495"},{"key":"ref2","author":"Saunders","year":"2021","journal-title":"Autonomous aerial delivery vehicles, a survey of techniques on how aerial package delivery is achieved"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2909530"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2750675.2750683"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijdrr.2025.105199"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2854712"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2009.5354646"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.089"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref10","article-title":"End-to-end navigation with vlms: Transforming spatial reasoning into question-answering","volume-title":"Workshop on Language and Robot Learning: Language as an Interface","author":"Goetting"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01549"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref14","author":"Kim","year":"2024","journal-title":"Openvla: An open-source vision-language-action model"},{"key":"ref15","author":"Ramakrishnan","year":"2021","journal-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref17","article-title":"Vision-based navigation with language-based assistance via imitation learning with indirect intervention","author":"Nguyen","year":"2018","journal-title":"CVPR 2019"},{"key":"ref18","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning (CoRL)","author":"Thomason"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01282"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1287"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2795643"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917702237"},{"key":"ref25","year":"2024","journal-title":"Introducing gemini 2.0: our new ai model for the agentic era"},{"key":"ref26","author":"Grattafiori","year":"2024","journal-title":"The llama 3 herd of models"},{"key":"ref27","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref28","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref29","author":"Jiang","year":"2023","journal-title":"Mistral 7b"},{"key":"ref30","author":"Brown","year":"2022","journal-title":"Do as i can, not as i say: Grounding language in robotic affordances"},{"key":"ref31","author":"Mao","year":"2023","journal-title":"Gpt-driver: Learning to drive with gpt"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref33","author":"You","year":"2025","journal-title":"Large language diffusion models"},{"key":"ref34","author":"Shah","year":"2022","journal-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action"},{"key":"ref35","author":"Zhang","year":"2024","journal-title":"Tinyl-lama: An open-source small language model"},{"key":"ref36","author":"Ren","year":"2023","journal-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00695"},{"key":"ref38","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.91"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref41","author":"Chen","year":"2023","journal-title":"Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents"}],"event":{"name":"2025 European Conference on Mobile Robots (ECMR)","location":"Padova, Italy","start":{"date-parts":[[2025,9,2]]},"end":{"date-parts":[[2025,9,5]]}},"container-title":["2025 European Conference on Mobile Robots (ECMR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11162725\/11162953\/11163198.pdf?arnumber=11163198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T04:42:19Z","timestamp":1758256939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11163198\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,2]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ecmr65884.2025.11163198","relation":{},"subject":[],"published":{"date-parts":[[2025,9,2]]}}}