{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:00:10Z","timestamp":1777654810928,"version":"3.51.4"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610890","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"7508-7514","source":"Crossref","is-referenced-by-count":12,"title":["Learning Language-Conditioned Deformable Object Manipulation with Graph Dynamics"],"prefix":"10.1109","author":[{"given":"Yuhong","family":"Deng","sequence":"first","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Mo","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongkun","family":"Xia","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812215"},{"key":"ref2","first-page":"192","article-title":"Fabricflownet: Bimanual cloth manipulation with a flow-based policy","volume-title":"Conference on Robot Learning","author":"Weng"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561391"},{"key":"ref4","first-page":"2317","article-title":"Learning arbitrary-goal fabric folding with one hour of real robot experience","volume-title":"Conference on Robot Learning","author":"Lee"},{"key":"ref5","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref6","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"6th Annual Conference on Robot Learning","author":"Brohan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3066969"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2022.3147415"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref11","first-page":"256","article-title":"Learning visible connectivity dynamics for cloth smoothing","volume-title":"Conference on Robot Learning","author":"Lin"},{"key":"ref12","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","first-page":"564","article-title":"Learning predictive representations for deformable objects using contrastive estimation","volume-title":"Conference on Robot Learning","author":"Yan"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811597"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989247"},{"key":"ref17","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","volume-title":"Conference on Robot Learning","author":"Matas"},{"key":"ref18","article-title":"Learning to manipulate deformable objects without demonstrations","author":"Wu","year":"2020","journal-title":"Robotics: Science and Systems"},{"key":"ref19","first-page":"1486","article-title":"Guiding multi-step rearrangement tasks with natural language instructions","volume-title":"Conference on Robot Learning","author":"Stengel-Eskin"},{"key":"ref20","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","author":"Shridhar","year":"2022"},{"key":"ref21","first-page":"1303","article-title":"Learning language-conditioned robot behavior from offline data and crowdsourced annotation","volume-title":"Conference on Robot Learning","author":"Nair"},{"key":"ref22","article-title":"Instruction-driven history-aware policies for robotic manipulations","author":"Guhur","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref24","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3229573"},{"key":"ref26","first-page":"13266","article-title":"Representing long-range context for graph neural networks with global attention","volume":"34","author":"Wu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"432","article-title":"Softgym: Benchmarking deep reinforcement learning for deformable object manipulation","volume-title":"Conference on Robot Learning","author":"Lin"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_21"},{"key":"ref29","first-page":"1303","article-title":"Learning language-conditioned robot behavior from offline data and crowd-sourced annotation","volume-title":"Conference on Robot Learning","author":"Nair"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610890.pdf?arnumber=10610890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:22:23Z","timestamp":1723267343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610890\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610890","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}