{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:44:49Z","timestamp":1766061889611,"version":"3.48.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247555","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"4083-4090","source":"Crossref","is-referenced-by-count":0,"title":["FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction"],"prefix":"10.1109","author":[{"given":"Dennis","family":"Rotondi","sequence":"first","affiliation":[{"name":"University of Stuttgart,Socially Intelligent Robotics Lab, Institute for Artificial Intelligence,Germany"}]},{"given":"Fabio","family":"Scaparro","sequence":"additional","affiliation":[{"name":"University of Stuttgart,Socially Intelligent Robotics Lab, Institute for Artificial Intelligence,Germany"}]},{"given":"Hermann","family":"Blum","sequence":"additional","affiliation":[{"name":"University of Bonn,Robot Perception and Learning Lab, LAMARR Institute for Machine Learning and Artificial Intelligence,Germany"}]},{"given":"Kai O.","family":"Arras","sequence":"additional","affiliation":[{"name":"University of Stuttgart,Socially Intelligent Robotics Lab, Institute for Artificial Intelligence,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2931042"},{"article-title":"Conceptgraphs: Open-vocabulary 3d scene graphs for perception and planning","volume-title":"ICRA","author":"Kuwajerwala","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01377"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.079"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.050"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3451395"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00743"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00337"},{"article-title":"Vlsat: Visual-linguistic semantics assisted training for 3d semantic scene graph prediction in point cloud","volume-title":"CVPR","author":"Wang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01345"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3544518"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00873"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"article-title":"OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views","volume-title":"ICLR","author":"Engelmann","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref23","article-title":"Learning transferable visual models from natural language supervision","volume":"139","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3534523"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00182"},{"article-title":"Partafford: Part-level affordance discovery from 3d objects","year":"2022","author":"Xu","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.4324\/9780203767764"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802558"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160747"},{"key":"ref31","article-title":"Multiscan: Scalable rgbd scanning for 3d environments with articulated objects","author":"Mao","year":"2022","journal-title":"NeurIPS"},{"key":"ref32","article-title":"ARKitscenes - a diverse real-world dataset for 3d indoor scene understanding using mobile RGB-d data","author":"Baruch","year":"2021","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610590"},{"key":"ref35","article-title":"Where2explore: Fewshot affordance learning for unseen novel categories of articulated objects","volume":"36","author":"Ning","year":"2023","journal-title":"NeurIPS"},{"article-title":"Adamanip: Adaptive articulated object manipulation environments and policy learning","volume-title":"ICLR","author":"Wang","key":"ref36"},{"article-title":"Towards fusing point cloud and visual representations for imitation learning","year":"2025","author":"Donat","key":"ref37"},{"key":"ref38","article-title":"Point cloud matters: Rethinking the impact of different observation spaces on robot learning","author":"Zhu","year":"2024","journal-title":"NeurIPS"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241229725"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"article-title":"Grounding dino 1.5: Advance the\u201dedge\" of open-set object detection","year":"2024","author":"Ren","key":"ref41"},{"article-title":"The bare necessities: Designing simple, effective open-vocabulary scene graphs","year":"2024","author":"Kassab","key":"ref42"},{"journal-title":"CoRR","article-title":"GPT-4 technical report","year":"2023","key":"ref43"},{"article-title":"Yolov11: An overview of the key architectural enhancements","year":"2024","author":"Khanam","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897990"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247555.pdf?arnumber=11247555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:12Z","timestamp":1766061612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247555","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}