{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:37Z","timestamp":1792786897376,"version":"4.5.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62306302"],"award-info":[{"award-number":["62306302"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Beijing Natural Science Foundation","award":["L258082"],"award-info":[{"award-number":["L258082"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3697634","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T19:34:54Z","timestamp":1780342494000},"page":"12301-12318","source":"Crossref","is-referenced-by-count":2,"title":["AeroVerse: UAV-Agent Benchmark Suite for Simulating, Pre-Training, Finetuning, and Evaluating Aerospace Embodied Foundation Models"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4187-9755","authenticated-orcid":false,"given":"Fanglong","family":"Yao","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5484-9195","authenticated-orcid":false,"given":"Yuanchang","family":"Yue","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7135-0321","authenticated-orcid":false,"given":"Youzhi","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9229-2121","authenticated-orcid":false,"given":"Zhigang","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4855-2464","authenticated-orcid":false,"given":"Lei","family":"Jin","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications (BUPT)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0294-8538","authenticated-orcid":false,"given":"Bin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3508-756X","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of AI (TeleAI), China Telecom","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0038-9816","authenticated-orcid":false,"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Fu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"DJI drone solutions for inspection and infrastructure construction in the oil and gas industry","volume-title":"Website","year":"2022"},{"key":"ref2","first-page":"10737","article-title":"ALFRED: A benchmark for interpreting grounded instructions for everyday tasks","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Shridhar","year":"2019"},{"key":"ref3","first-page":"4392","article-title":"Room-across-room: Multilingual vision-and-language navigation with dense spatiotemporal grounding","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Ku","year":"2020"},{"key":"ref4","first-page":"455","article-title":"iGibson 2.0: Object-centric simulation for robot learning of everyday household tasks","volume-title":"Proc. 5th Conf. Robot Learn.","volume":"164","author":"Li","year":"2022"},{"key":"ref5","first-page":"9979","article-title":"REVERIE: Remote embodied visual referring expression in real indoor environments","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi","year":"2019"},{"key":"ref6","first-page":"7520","article-title":"iGibson 1.0: A simulation environment for interactive tasks in large realistic scenes","volume-title":"Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst.","author":"Shen","year":"2021"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1109\/LRA.2020.2965078","article-title":"Interactive Gibson benchmark: A benchmark for interactive navigation in cluttered environments","volume":"5","author":"Xia","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.59717\/j.xinn-inform.2025.100015"},{"key":"ref9","first-page":"20413","article-title":"An embodied generalist agent in 3D world","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2024"},{"key":"ref10","first-page":"20482","article-title":"3D-LLM: Injecting the 3D World into Large Language Models","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"36","author":"Hong","year":"2023"},{"key":"ref11","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Driess","year":"2023"},{"key":"ref12","first-page":"2165","article-title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","volume-title":"Proc. 7th Conf. Robot Learn., ser. Proc. Mach. Learn. Res.","volume":"229","author":"Zitkovich","year":"2023"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.52202\/075280-1090","article-title":"EmbodiedGPT: Vision-language pre-training via embodied chain of thought","author":"Mu","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i28.39562"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_6"},{"key":"ref18","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni","year":"2002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref20","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref21","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref22","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref23","article-title":"Fine-tuning language models from human preferences","author":"Ziegler","year":"2019"},{"key":"ref24","first-page":"46595","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zheng","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01854"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-022-01490-7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01075"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591508"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref34","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref35","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li","year":"2023"},{"key":"ref36","article-title":"LLaMA-adapter V2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref37","first-page":"18378","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref38","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref40","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref41","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics","author":"Roukos","year":"2002"},{"key":"ref42","first-page":"4566","article-title":"CIDEr: Consensus-based image description evaluation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Vedantam","year":"2014"},{"key":"ref43","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11538323.pdf?arnumber=11538323","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:04:07Z","timestamp":1790269447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11538323\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":43,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3697634","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}