{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:39:42Z","timestamp":1766061582190,"version":"3.48.0"},"reference-count":33,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247213","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"4142-4149","source":"Crossref","is-referenced-by-count":0,"title":["Domain-Conditioned Scene Graphs for State-Grounded Task Planning"],"prefix":"10.1109","author":[{"given":"Jonas","family":"Herzog","sequence":"first","affiliation":[{"name":"Zhejiang University"}]},{"given":"Jiangpin","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]}],"member":"263","reference":[{"article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable task planning","volume-title":"Conference on Robot Learning (CoRL)","author":"Rana","key":"ref1"},{"article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning (CoRL)","author":"Ahn","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3471457"},{"key":"ref4","article-title":"Grounded decoding: Guiding text generation with grounded models for robot control","author":"Huang","year":"2023","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"article-title":"Can-do! a dataset and neuro-symbolic grounded framework for embodied planning with large multimodal models","year":"2024","author":"Chia","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611112"},{"article-title":"Look before you leap: Unveiling the power of gpt-4v in robotic vision-language planning","year":"2023","author":"Hu","key":"ref7"},{"article-title":"Veri-graph: Scene graphs for execution verifiable robot planning","year":"2024","author":"Ekpo","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801291"},{"key":"ref10","article-title":"Pddl-the planning domain definition language","volume-title":"Tech Report","author":"McDermott","year":"1998"},{"article-title":"Llm+p: Empowering large language models with optimal planning proficiency","year":"2023","author":"Liu","key":"ref11"},{"key":"ref12","article-title":"Described object detection: Liberating object detection with flexible expressions","author":"Xie","year":"2023","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref13","article-title":"Regression planning networks","author":"Xu","year":"2019","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561548"},{"article-title":"Sornet: Spatial object-centric representations for sequential manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Yuan","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196597"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.30006"},{"article-title":"Task and motion planning in hierarchical 3d scene graphs","year":"2024","author":"Ray","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"article-title":"Llm-state: Open world state representation for long-horizon task planning with large language model","year":"2023","author":"Chen","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981735"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1705"},{"article-title":"Dino-x: A unified vision model for open-world object detection and understanding","year":"2024","author":"Ren","key":"ref24"},{"article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","year":"2023","author":"Yang","key":"ref25"},{"article-title":"Minicpm-v: A gpt-4v level mllm on your phone","year":"2024","author":"Yao","key":"ref26"},{"article-title":"Xgen-mm (blip-3): A family of open large multimodal models","year":"2024","author":"Xue","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01979"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72907-2_12"},{"key":"ref33","article-title":"Revisiting few-shot object detection with vision-language models","author":"Madan","year":"2024","journal-title":"Neural Information Processing Systems (NeurIPS)"}],"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\/11247213.pdf?arnumber=11247213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:34:42Z","timestamp":1766061282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247213\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247213","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}