{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:36:51Z","timestamp":1757608611847,"version":"3.44.0"},"reference-count":38,"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\/501100012166","name":"the National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFB4503701"],"award-info":[{"award-number":["2023YFB4503701"]}],"id":[{"id":"10.13039\/501100012166","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\/icra55743.2025.11128194","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"11933-11939","source":"Crossref","is-referenced-by-count":0,"title":["Interaction-Driven Updates: 3D Scene Graph Maintenance During Robot Task Execution"],"prefix":"10.1109","author":[{"given":"Qingfeng","family":"Li","sequence":"first","affiliation":[{"name":"Beihang University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinlei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Hangzhou Innovation Institute of Beihang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haochen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beihang University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Niu","sequence":"additional","affiliation":[{"name":"Beihang University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref2","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning","volume-title":"7th Annual Conference on Robot Learning","author":"Rana","key":"ref3"},{"key":"ref4","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International conference on machine learning. PMLR","author":"Huang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref6","article-title":"Llm as a robotic brain: Unifying egocentric memory and control","author":"Mai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801291"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2931042"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211056674"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_21"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.050"},{"key":"ref14","first-page":"46","article-title":"Taskography: Evaluating robot task planning over large 3d scene graphs","volume-title":"Conference on Robot Learning","author":"Agia"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560736"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/2300000059"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.25080\/TCWV9851"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635985"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref20","article-title":"Ai2-thor: An interactive 3d environment for visual ai","author":"Kolve","year":"2017","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"ref22","first-page":"19730","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning. PMLR","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5648920"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385561"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2016.7535485"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487237"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061363"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811916"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref30","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00743"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00337"},{"key":"ref36","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Alexey","year":"2020","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611489"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01245"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11128194.pdf?arnumber=11128194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:07:02Z","timestamp":1756879622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128194","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}