{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:53:20Z","timestamp":1772909600200,"version":"3.50.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2124857"],"award-info":[{"award-number":["2124857"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127471","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"2853-2860","source":"Crossref","is-referenced-by-count":2,"title":["Point2Graph: An End-to-End Point Cloud-Based 3D Open-Vocabulary Scene Graph for Robot Navigation"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Xu","sequence":"first","affiliation":[{"name":"University of Michigan,Ann Arbor,MI,USA,48109"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziming","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor,MI,USA,48109"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianwei","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor,MI,USA,48109"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vineet","family":"Kamat","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor,MI,USA,48109"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carol","family":"Menassa","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor,MI,USA,48109"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/S0004-3702(00)00017-5","article-title":"The spatial semantic hierarchy","volume":"119","author":"Kuipers","year":"2000","journal-title":"Artificial Intelligence"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2020.XVI.079","article-title":"3D dynamic scene graphs: Actionable spatial perception with places, objects, and humans","volume-title":"Robotics: Science and Systems (RSS)","author":"Rosinol","year":"2020"},{"issue":"5","key":"ref3","doi-asserted-by":"crossref","DOI":"10.3390\/ijgi9050330","article-title":"A review of techniques for 3d reconstruction of indoor environments","volume":"9","author":"Kang","year":"2020","journal-title":"ISPRS International Journal of Geo-Information"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref5","article-title":"LM-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"6th Annual Conference on Robot Learning","author":"Shah","year":"2022"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA48891.2023.10160396","volume-title":"Grounding language with visual affordances over unstructured data","author":"Mees","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.077"},{"key":"ref9","article-title":"Conceptgraphs: Open-vocabulary 3d scene graphs for perception and planning","author":"Gu","year":"2023","journal-title":"arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref11","article-title":"AI2-THOR: An Interactive 3D Environment for Visual AI","author":"Kolve","year":"2017","journal-title":"arXiv"},{"key":"ref12","volume-title":"Openins3d: Snap and lookup for 3d open-vocabulary instance segmentation","author":"Huang","year":"2024"},{"key":"ref13","first-page":"73","article-title":"From bim to pointcloud: Automatic generation of labeled indoor pointcloud","volume":"XLIII-B5\u20132022","author":"Huang","year":"2022","journal-title":"The International Archives of the Photogrammetry"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02076"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3156953"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1109\/SAMI50585.2021.9378657","article-title":"Occlusion handling in generic object detection: A review","volume-title":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI). IEEE","author":"Saleh","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241229725"},{"key":"ref19","article-title":"Scenegraphfusion: Incremental 3d scene graph prediction from RGB-D sequences","volume":"abs\/2103.14898","author":"Wu","year":"2021","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.050"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211056674"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","author":"Yang","year":"2023","journal-title":"Sam3d: Segment anything in 3d scenes"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570263"},{"issue":"1","key":"ref25","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/S0004-3702(97)00078-7","article-title":"Learning metric-topological maps for indoor mobile robot navigation","volume":"99","author":"Thrun","year":"1998","journal-title":"Artif. Intell."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487234"},{"key":"ref27","volume-title":"Heat: Holistic edge attention transformer for structured reconstruction","author":"Chen","year":"2022"},{"key":"ref28","volume-title":"Connecting the dots: Floorplan reconstruction using two-level queries","author":"Yue","year":"2023"},{"key":"ref29","volume-title":"Questmaps: Queryable semantic topological maps for 3d scene understanding","author":"Mehan","year":"2024"},{"key":"ref30","article-title":"Uni3d: Exploring unified 3d representation at scale","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_13"},{"key":"ref32","article-title":"Openmask3d: Open-vocabulary 3d instance segmentation","author":"Takmaz","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref36","article-title":"V-detr: Detr with vertex relative position encoding for 3d object detection","author":"Shen","year":"2023","journal-title":"arXiv preprint"},{"issue":"34","key":"ref37","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","volume":"96","author":"Ester","year":"1996","journal-title":"kdd"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISVD.2007.43"},{"key":"ref39","article-title":"New embedding models and api updates","volume-title":"OpenAI","year":"2023"},{"key":"ref40","volume-title":"Gpt-4 technical report","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01874"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3410324"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref46","volume-title":"Conav chair: Design of a ros-based smart wheelchair for shared control navigation in the built environment","author":"Xu","year":"2025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2012.6463060"},{"key":"ref48","article-title":"A gentle introduction to conformal prediction and distribution-free uncertainty quantification","volume":"abs\/2107.07511","author":"Angelopoulos","year":"2021","journal-title":"CoRR"},{"key":"ref49","volume-title":"Seeing with partial certainty: Conformal prediction for robotic scene recognition in built environments","author":"Xu","year":"2025"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127471.pdf?arnumber=11127471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:11:37Z","timestamp":1756879897000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127471","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}