{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:31:55Z","timestamp":1773376315986,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3776734.3794353","type":"proceedings-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:05:48Z","timestamp":1773345948000},"page":"52-56","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DiffusionCinema: Text-to-Aerial Cinematography"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3285-3937","authenticated-orcid":false,"given":"Valerii","family":"Serpiva","sequence":"first","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6119-2366","authenticated-orcid":false,"given":"Artem","family":"Lykov","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8635-5379","authenticated-orcid":false,"given":"Jeffrin","family":"Sam","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2506-9111","authenticated-orcid":false,"given":"Aleksey","family":"Fedoseev","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8055-5345","authenticated-orcid":false,"given":"Dzmitry","family":"Tsetserukou","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Anthony Brohan et al. 2023. RT-1: Robotics Transformer for Real-World Control at Scale. arxiv:2212.06817. arxiv:2212.06817"},{"key":"e_1_3_2_2_2_1","unstructured":"Anthony Brohan Noah Brown et al. 2023. RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control. arxiv:2307.15818. arxiv:2307.15818"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14214312"},{"key":"e_1_3_2_2_5_1","unstructured":"Yunpeng Gao Zhigang Wang Linglin Jing Dong Wang Xuelong Li and Bin Zhao. 2024. Aerial Vision-and-Language Navigation via Semantic-Topo-Metric Representation Guided LLM Reasoning. arxiv:2410.08500. arxiv:2410.08500"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Patrick Geneva Kevin Eckenhoff Woosik Lee Yulin Yang and Guoquan Huang. 2020. OpenVINS: A Research Platform for Visual-Inertial Estimation. 4666-4672 pages. https:\/\/api.semanticscholar.org\/CorpusID:204745914","DOI":"10.1109\/ICRA40945.2020.9196524"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3400838"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1037\/e577632012-009"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS65942.2025.11007799"},{"key":"e_1_3_2_2_10_1","unstructured":"Moo Jin Kim Karl Pertsch Siddharth Karamcheti Ted Xiao Ashwin Balakrishna Suraj Nair Rafael Rafailov Ethan Foster Grace Lam Pannag Sanketi Quan Vuong Thomas Kollar Benjamin Burchfiel Russ Tedrake Dorsa Sadigh Sergey Levine Percy Liang and Chelsea Finn. 2024. OpenVLA: An Open-Source Vision-Language-Action Model. arxiv:2406.09246. arxiv:2406.09246"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89350-9_6"},{"key":"e_1_3_2_2_12_1","unstructured":"Jungdae Lee Taiki Miyanishi Shuhei Kurita Koya Sakamoto Daichi Azuma Yutaka Matsuo and Nakamasa Inoue. 2025. CityNav: A Large-Scale Dataset for Real-World Aerial Navigation. arxiv:2406.14240. arxiv:2406.14240"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01411"},{"key":"e_1_3_2_2_14_1","volume-title":"Oleg Sautenkov, Artyom Myshlyaev, Grik Tadevosyan, Yasheerah Yaqoot, and Dzmitry Tsetserukou.","author":"Lykov Artem","year":"2025","unstructured":"Artem Lykov, Valerii Serpiva, Muhammad Haris Khan, Oleg Sautenkov, Artyom Myshlyaev, Grik Tadevosyan, Yasheerah Yaqoot, and Dzmitry Tsetserukou. 2025. CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs. arxiv:2503.01378. arxiv:2503.01378"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486586"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3347713"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064282"},{"key":"e_1_3_2_2_18_1","unstructured":"NVIDIA Research. 2025. World Simulation with Video Foundation Models for Physical AI. (Core World Model)"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3157626"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10974117"},{"key":"e_1_3_2_2_21_1","volume-title":"Miguel Altamirano Cabrera, and Dzmitry Tsetserukou","author":"Serpiva Valerii","year":"2025","unstructured":"Valerii Serpiva, Artem Lykov, Faryal Batool, Vladislav Kozlovskiy, Miguel Altamirano Cabrera, and Dzmitry Tsetserukou. 2025. FlightDiffusion: Revolutionising Autonomous Drone Training with Diffusion Models Generating FPV Video. arxiv:2509.14082. arxiv:2509.14082"},{"key":"e_1_3_2_2_22_1","volume-title":"Ali Alridha Abdulkarim, Oleg Sautenkov, and Dzmitry Tsetserukou.","author":"Serpiva Valerii","year":"2025","unstructured":"Valerii Serpiva, Artem Lykov, Artyom Myshlyaev, Muhammad Haris Khan, Ali Alridha Abdulkarim, Oleg Sautenkov, and Dzmitry Tsetserukou. 2025. RaceVLA: VLA-based Racing Drone Navigation with Human-like Behaviour. arxiv:2503.02572. arxiv:2503.02572"},{"key":"e_1_3_2_2_23_1","unstructured":"Xiangyu Wang Donglin Yang Ziqin Wang Hohin Kwan Jinyu Chen Wenjun Wu Hongsheng Li Yue Liao and Si Liu. 2024. Towards Realistic UAV Vision-Language Navigation: Platform Benchmark and Methodology. https:\/\/api.semanticscholar.org\/CorpusID:273233904"},{"key":"e_1_3_2_2_24_1","unstructured":"Xiangyu Wang Donglin Yang Ziqin Wang Hohin Kwan Jinyu Chen Wenjun Wu Hongsheng Li Yue Liao and Si Liu. 2024. Towards Realistic UAV Vision-Language Navigation: Platform Benchmark and Methodology. arxiv:2410.07087"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","unstructured":"Wenjing Xiao Chenglong Shi Miaojiang Chen Athanasios V. Vasilakos Min Chen and Ahmed Farouk. 2025. LLM-based UAV Path Planning for Autonomous and Adaptive Industry Systems. issn:1556-4665 https:\/\/doi.org\/10.1145\/3774655 Just Accepted 10.1145\/3774655","DOI":"10.1145\/3774655"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-6495-6_31"},{"key":"e_1_3_2_2_27_1","volume-title":"ChatGPT for Robotics: A New Approach to Human-Robot Interaction and Task Planning","author":"Xie Bing","unstructured":"Bing Xie, Xiangming Xi, Xinan Zhao, Yuhan Wang, Wei Song, Jianjun Gu, and Shiqiang Zhu. 2023. ChatGPT for Robotics: A New Approach to Human-Robot Interaction and Task Planning. In Intelligent Robotics and Applications, Huayong Yang, Honghai Liu, Jun Zou, Zhouping Yin, Lianqing Liu, Geng Yang, Xiaoping Ouyang, and Zhiyong Wang (Eds.). Springer Nature Singapore, Singapore. 365\u2013376. isbn:978-981-99-6495-6"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","unstructured":"Weichen Zhang Yuxuan Liu Xuzhe Wang Xuecheng Chen Chen Gao and Xinlei Chen. 2024. Demo Abstract: Embodied Aerial Agent for City-level Visual Language Navigation Using Large Language Model. In 2024 23rd ACM\/IEEE International Conference on Information Processing in Sensor Networks (IPSN). IEEE Press 265\u2013266. https:\/\/doi.org\/10.1109\/IPSN61024.2024.00033 10.1109\/IPSN61024.2024.00033","DOI":"10.1109\/IPSN61024.2024.00033"},{"key":"e_1_3_2_2_30_1","volume-title":"Valerii Serpiva, Ali Alridha Abdulkarim, Aleksey Fedoseev, Didar Seyidov, Hajira Amjad, and Dzmitry Tsetserukou.","author":"Zhura Iana","year":"2025","unstructured":"Iana Zhura, Sausar Karaf, Faryal Batool, Nipun Dhananjaya Weerakkodi Mudalige, Valerii Serpiva, Ali Alridha Abdulkarim, Aleksey Fedoseev, Didar Seyidov, Hajira Amjad, and Dzmitry Tsetserukou. 2025. SwarmDiffusion: End-To-End Traversability-Guided Diffusion for Embodiment-Agnostic Navigation of Heterogeneous Robots. arxiv:2512.02851. arxiv:2512.02851"}],"event":{"name":"HRI '26: 21st ACM\/IEEE International Conference on Human-Robot Interaction","location":"Edinburgh Scotland UK","acronym":"HRI '26","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction","IEEE RAS"]},"container-title":["Companion Proceedings of the 21st ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:09:34Z","timestamp":1773346174000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3776734.3794353"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":30,"alternative-id":["10.1145\/3776734.3794353","10.1145\/3776734"],"URL":"https:\/\/doi.org\/10.1145\/3776734.3794353","relation":{},"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"2026-03-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}