{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T11:28:42Z","timestamp":1769772522662,"version":"3.49.0"},"reference-count":46,"publisher":"Informa UK Limited","issue":"1","content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Advanced Robotics"],"published-print":{"date-parts":[[2026,1,2]]},"DOI":"10.1080\/01691864.2025.2599950","type":"journal-article","created":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T12:35:16Z","timestamp":1765715716000},"page":"10-24","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":0,"title":["Visual robot navigation adaptive to directional cues using vision-language models and conditional diffusion models"],"prefix":"10.1080","volume":"40","author":[{"given":"Shintaro","family":"Nakaoka","sequence":"first","affiliation":[{"name":"Toyota Motor Corporation","place":["Toyota, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kosei","family":"Tanada","sequence":"additional","affiliation":[{"name":"Toyota Motor Corporation","place":["Toyota, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhito","family":"Tanaka","sequence":"additional","affiliation":[{"name":"Toyota Motor Corporation","place":["Toyota, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuma","family":"Sugino","sequence":"additional","affiliation":[{"name":"Toyota Motor Corporation","place":["Toyota, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Kondo","sequence":"additional","affiliation":[{"name":"Toyota Motor Corporation","place":["Toyota, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shigemichi","family":"Matsuzaki","sequence":"additional","affiliation":[{"name":"Toyota Motor Corporation","place":["Toyota, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_5_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2024.2408593"},{"key":"e_1_3_5_3_1","doi-asserted-by":"publisher","DOI":"10.5391\/IJFIS.2013.13.2.140"},{"key":"e_1_3_5_4_1","unstructured":"Cuan C Lee E Fisher E et\u00a0al. Gesture2Path: imitation learning for gesture-aware navigation; 2022. (Tech Rep. 2209.09375). http:\/\/arxiv.org\/abs\/2209.09375."},{"key":"e_1_3_5_5_1","unstructured":"Abdin M Aneja J Awadalla H et\u00a0al. Phi-3 technical report: a highly capable language model locally on your phone; 2024 Apr. (Tech Rep). http:\/\/arxiv.org\/abs\/2404.14219."},{"key":"e_1_3_5_6_1","unstructured":"Openai. Gpt-4v(ision) system card; 2023. (Tech Rep)."},{"key":"e_1_3_5_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"e_1_3_5_8_1","unstructured":"Ho J Salimans T. Classifier-free diffusion guidance. In: International Conference on Neural Information Processing Systems Workshop. Curran Associates Inc; 2021 Dec."},{"key":"e_1_3_5_9_1","unstructured":"Dhariwal P Nichol A. Diffusion models beat GANs on image synthesis. In: International Conference on Neural Information Processing Systems. Curran Associates Inc.; 2021 Dec. p. 8780\u20138794."},{"key":"e_1_3_5_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_5_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127466"},{"key":"e_1_3_5_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.982903"},{"key":"e_1_3_5_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-008-9235-4"},{"key":"e_1_3_5_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016"},{"key":"e_1_3_5_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3193464"},{"key":"e_1_3_5_16_1","unstructured":"Shah D Sridhar A Dashora N et al. ViNT: a foundation model for visual navigation. In: Conference on Robot Learning; Atlanta. PMLR; 2023 Nov."},{"key":"e_1_3_5_17_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"e_1_3_5_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1999.770051"},{"key":"e_1_3_5_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389771"},{"key":"e_1_3_5_20_1","unstructured":"Klasing K Lidoris G Bauer A et\u00a0al. The autonomous city explorer : towards semantic navigation in urban environments. In: International Workshop on Cognition for Technical Systems; 2008."},{"key":"e_1_3_5_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1734454.1734468"},{"key":"e_1_3_5_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8664854"},{"key":"e_1_3_5_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342107"},{"key":"e_1_3_5_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/GPC.WORKSHOPS.2008.41"},{"key":"e_1_3_5_25_1","unstructured":"Sabikan S Sulaiman M Salim N et al. Vision\u2013based automated guided vehicle for navigation and obstacle avoidance. In: International Conference on Engineering and ICT; Melaka. 2010 Feb. p. 18\u201320."},{"key":"e_1_3_5_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980164"},{"key":"e_1_3_5_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20041181"},{"key":"e_1_3_5_28_1","unstructured":"Yang S Nachum O Du Y et\u00a0al. Foundation models for decision making: problems methods and opportunities; 2023 Mar. (Tech Rep. 2303.04129). http:\/\/arxiv.org\/abs\/2303.04129."},{"key":"e_1_3_5_29_1","unstructured":"Firoozi R Tucker J Tian S et\u00a0al. Foundation models in robotics : applications challenges and the future; 2023. (Tech Rep). arXiv:2312.07843v1."},{"key":"e_1_3_5_30_1","unstructured":"Shah D Osinski B Ichter B et\u00a0al. LM-Nav: robotic navigation with large pre-trained models of language vision and action. In: Conference on Robot Learning. PMLR; 2022."},{"key":"e_1_3_5_31_1","unstructured":"Shah D Equi M Osinski B et al. Navigation with large language models: semantic guesswork as a heuristic for planning. In: Conference on Robot Learning; Atlanta. PMLR; 2023 Nov."},{"key":"e_1_3_5_32_1","unstructured":"Biggie H Mopidevi AN Woods D et al. Tell me where to go: a composable framework for context-aware embodied robot navigation. In: Conference on Robot Learning; Atlanta. PMLR; 2023 Nov."},{"key":"e_1_3_5_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3441495"},{"key":"e_1_3_5_34_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"key":"e_1_3_5_35_1","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2024.2393409"},{"key":"e_1_3_5_36_1","unstructured":"Hirose N Sridhar A Glossop C et al. LeLaN: learning a language-conditioned navigation policy from in-the-wild video. In: Conference on Robot Learning; Munich. PMLR; 2024 Nov."},{"key":"e_1_3_5_37_1","unstructured":"Tanada K Matsuzaki S Tanaka K et al. Pointing gesture understanding via visual prompting and visual question answering for interactive robot navigation. In: IEEE International Conference on Robotics and Automation Workshop; Yokohama. IEEE; 2024 May."},{"key":"e_1_3_5_38_1","unstructured":"Radford A Kim JW Hallacy C et\u00a0al. Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. PMLR; 2021 Feb. p.\u00a08748\u20138763."},{"key":"e_1_3_5_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_5_40_1","unstructured":"Betker J Goh G Jing L et\u00a0al. Improving image generation with better captions; 2023. (Tech Rep)."},{"key":"e_1_3_5_41_1","unstructured":"Tochilkin D Pankratz D Liu Z et\u00a0al. Triposr: fast 3d object reconstruction from a single image; 2024 Mar. (Tech Rep). http:\/\/arxiv.org\/abs\/2403.02151."},{"key":"e_1_3_5_42_1","unstructured":"GeminiTeam. Gemini: a family of highly capable multimodal models; 2023 Dec. (Tech Rep). http:\/\/arxiv.org\/abs\/2312.11805."},{"key":"e_1_3_5_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_5_44_1","unstructured":"Ho J Jain A Abbeel P. Denoising diffusion probabilistic models. In: International Conference on Neural Information Processing Systems. Carran Associates Inc.; 2020 Dec."},{"key":"e_1_3_5_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_5_46_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40648-019-0132-3"},{"key":"e_1_3_5_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583741"}],"container-title":["Advanced Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01691864.2025.2599950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T18:28:49Z","timestamp":1769711329000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01691864.2025.2599950"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,2]]}},"alternative-id":["10.1080\/01691864.2025.2599950"],"URL":"https:\/\/doi.org\/10.1080\/01691864.2025.2599950","relation":{},"ISSN":["0169-1864","1568-5535"],"issn-type":[{"value":"0169-1864","type":"print"},{"value":"1568-5535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2025-03-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-26","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}