{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:18:17Z","timestamp":1792599497622,"version":"4.5.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006369","name":"George Mason University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006369","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247618","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"17192-17198","source":"Crossref","is-referenced-by-count":9,"title":["Social-LLaVA: Enhancing Social Robot Navigation through Human-Language Reasoning"],"prefix":"10.1109","author":[{"given":"Amirreza","family":"Payandeh","sequence":"first","affiliation":[{"name":"George Mason University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daeun","family":"Song","sequence":"additional","affiliation":[{"name":"George Mason University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Nazeri","sequence":"additional","affiliation":[{"name":"George Mason University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Liang","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Praneel","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"George Mason University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir Hossain","family":"Raj","sequence":"additional","affiliation":[{"name":"George Mason University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangzhe","family":"Kong","sequence":"additional","affiliation":[{"name":"George Mason University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuesu","family":"Xiao","sequence":"additional","affiliation":[{"name":"George Mason University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3700599"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2013.6698863"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342447"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0017.00175"},{"key":"ref8","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023"},{"key":"ref9","article-title":"Drivelm: Driving with graph visual question answering","author":"Sima","year":"2024"},{"key":"ref10","article-title":"Lingoqa: Video question answering for autonomous driving","author":"Marcu","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.52202\/079017-4293","article-title":"Spatialrgpt: Grounded spatial reasoning in vision language models","author":"Cheng","year":"2024"},{"key":"ref13","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref14","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref15","article-title":"Gemini: a family of highly capable multimodal models","author":"Anil","year":"2023"},{"key":"ref16","article-title":"Lima: Less is more for alignment","author":"Zhou","year":"2023"},{"key":"ref17","article-title":"Instructiongpt-4: A 200-instruction paradigm for fine-tuning minigpt-4","author":"Wei","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3583741"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3647983"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3511409"},{"key":"ref21","article-title":"A protocol for validating social navigation policies","author":"Pirk","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696576"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1957656.1957786"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.09.026"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2588880"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3329626"},{"key":"ref27","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref28","article-title":"Svit: Scaling up visual instruction tuning","author":"Zhao","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02572-7"},{"key":"ref30","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2015"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.02085","article-title":"Jrdb-social: A multifaceted robotic dataset for understanding of context and dynamics of human interactions within social groups","author":"Jahangard","year":"2024"},{"key":"ref32","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.4324\/9780203769942"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/9780262514620.001.0001","volume-title":"Vision : a computational investigation into the human representation and processing of visual information","author":"Marr","year":"2010"},{"key":"ref35","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247618.pdf?arnumber=11247618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:38:44Z","timestamp":1766061524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247618","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}