{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:18:15Z","timestamp":1778080695911,"version":"3.51.4"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801291","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"13765-13772","source":"Crossref","is-referenced-by-count":19,"title":["GRID: Scene-Graph-based Instruction-driven Robotic Task Planning"],"prefix":"10.1109","author":[{"given":"Zhe","family":"Ni","sequence":"first","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Xiaoxin","family":"Deng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Cong","family":"Tai","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Xinyue","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Qinghongbing","family":"Xie","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Weihang","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Xiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen Pudu Technology Inc.,Shenzhen,China"}]},{"given":"Long","family":"Zeng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref2","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref3","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Conference on Robot Learning","author":"Zitkovich"},{"key":"ref4","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning","author":"Brohan"},{"key":"ref5","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref6","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023"},{"key":"ref7","article-title":"Alphablock: Embodied finetuning for vision-language reasoning in robot manipulation","author":"Jin","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"ref9","article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","volume":"36","author":"Mu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.079"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00743"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00490"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01345"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561548"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3157567"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01670-0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341186"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01007"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.71"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26889-2_13"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460646"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812179"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981735"},{"key":"ref27","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable task planning","author":"Rana","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-101119-071628"},{"key":"ref29","article-title":"Can an embodied agent find your","author":"Dorbala","year":"2023","journal-title":"IEEE Robotics and Automation Letters"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref31","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295255"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"issue":"20","key":"ref34","first-page":"10","article-title":"Graph attention networks","volume":"1050","author":"Velickovic","year":"2017","journal-title":"stat"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2023.1221739"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01873"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611489"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801291.pdf?arnumber=10801291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:06:25Z","timestamp":1735196785000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801291","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}