{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T17:55:54Z","timestamp":1790186154618,"version":"4.1.0"},"reference-count":45,"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"}]},{"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"}]},{"DOI":"10.13039\/501100004260","name":"Renmin University of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004260","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\/icra57147.2024.10610744","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T13:51:05Z","timestamp":1723125065000},"page":"2073-2080","source":"Crossref","is-referenced-by-count":22,"title":["Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs"],"prefix":"10.1109","author":[{"given":"Wenke","family":"Xia","sequence":"first","affiliation":[{"name":"Renmin University of China,Gaoling School of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xincheng","family":"Pang","sequence":"additional","affiliation":[{"name":"Renmin University of China,Gaoling School of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhigang","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Hu","sequence":"additional","affiliation":[{"name":"Renmin University of China,Gaoling School of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Jia","year":"2023","journal-title":"Chain-of-thought predictive control"},{"key":"ref2","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161571"},{"key":"ref4","author":"Gu","year":"2023","journal-title":"Maniskill2: A unified benchmark for generalizable manipulation skills"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref6","author":"Brohan","year":"2023","journal-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref8","author":"Shi","year":"2023","journal-title":"Waypoint-based imitation learning for robotic manipulation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611293"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01717"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341846"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320012"},{"key":"ref13","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","author":"Wei","year":"2022","journal-title":"Emergent abilities of large language models"},{"key":"ref15","author":"Mirchandani","year":"2023","journal-title":"Large language models as general pattern machines"},{"key":"ref16","author":"Mandi","year":"2023","journal-title":"Roco: Dialectic multi-robot collaboration with large language models"},{"key":"ref17","author":"Huang","year":"2023","journal-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models"},{"key":"ref18","author":"Makoviychuk","year":"2021","journal-title":"Isaac gym: High performance gpu-based physics simulation for robot learning"},{"key":"ref19","author":"Zhang","year":"2023","journal-title":"Affordance-driven next-best-view planning for robotic grasping"},{"key":"ref20","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"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01117"},{"key":"ref22","author":"Mandi","year":"2022","journal-title":"Cacti: A framework for scalable multi-task multi-scene visual imitation learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.010"},{"key":"ref24","first-page":"15 084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref25","author":"Ren","year":"2023","journal-title":"Robots that ask for help: Uncertainty alignment for large language model planners"},{"key":"ref26","author":"Huang","year":"2022","journal-title":"Inner monologue: Embodied reasoning through planning with language models"},{"key":"ref27","author":"Zhou","year":"2023","journal-title":"Navgpt: Explicit reasoning in vision-and-language navigation with large language models"},{"key":"ref28","author":"Ahn","year":"2022","journal-title":"Do as i can, not as i say: Grounding language in robotic affordances"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341577"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161534"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.395"},{"key":"ref32","author":"Wu","year":"2023","journal-title":"Embodied task planning with large language models"},{"key":"ref33","author":"Zhu","year":"2023","journal-title":"Ghost in the minecraft: Generally capable agents for open-world enviroments via large language models with text-based knowledge and memory"},{"key":"ref34","author":"Yuan","year":"2023","journal-title":"Plan4mc: Skill reinforcement learning and planning for open-world minecraft tasks"},{"key":"ref35","author":"Driess","year":"2023","journal-title":"Palm-e: An embodied multimodal language model"},{"key":"ref36","first-page":"20","article-title":"Chatgpt for robotics: Design principles and model abilities","volume":"2","author":"Vemprala","year":"2023","journal-title":"Microsoft Auton. Syst. Robot. Res"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref39","author":"Yu","year":"2023","journal-title":"Language to rewards for robotic skill synthesis"},{"key":"ref40","article-title":"Towards a unified agent with foundation models","volume-title":"Workshop on Reincarnating Reinforcement Learning at ICLR 2023","author":"Palo"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00684"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01439"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref45","author":"Liu","year":"2023","journal-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection"}],"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\/10610744.pdf?arnumber=10610744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T01:20:50Z","timestamp":1723252850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610744","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}