{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:28:59Z","timestamp":1766068139534,"version":"3.32.0"},"reference-count":62,"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"}],"funder":[{"DOI":"10.13039\/501100018631","name":"Shanghai Platform for Neuromorphic and AI Chip","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018631","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801446","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"9676-9683","source":"Crossref","is-referenced-by-count":4,"title":["Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models"],"prefix":"10.1109","author":[{"given":"Tianyu","family":"Wang","sequence":"first","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haitao","family":"Lin","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junqiu","family":"Yu","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICRA46639.2022.9812372"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/IROS55552.2023.10342331"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1126\/science.aat8414"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICCV51070.2023.00029"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1146\/annurev-control-101119-071628"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICRA46639.2022.9811367"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR52729.2023.02223"},{"year":"2023","author":"Zhao","article-title":"A survey of large language models","key":"ref8"},{"year":"2023","author":"Mai","article-title":"Llm as a robotic brain: Unifying egocentric memory and control","key":"ref9"},{"year":"2023","author":"Huang","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","key":"ref10"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/IROS55552.2023.10341577"},{"key":"ref12","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"},{"year":"2023","author":"Huang","article-title":"Grounded decoding: Guiding text generation with grounded models for robot control","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ACCESS.2023.3310935"},{"key":"ref15","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"},{"year":"2023","author":"Achiam","article-title":"Gpt-4 technical report","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/IROS55552.2023.10342021"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2019.00275"},{"year":"2021","author":"Roy","article-title":"From machine learning to robotics: challenges and opportunities for embodied intelligence","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.3390\/s23031611"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ACCESS.2024.3387941"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICCV48922.2021.00354"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/IROS51168.2021.9636212"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1007\/978-3-031-20077-9_2"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/ICCV48922.2021.00277"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/CVPR52688.2022.00659"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CVPR46437.2021.00163"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/CVPR52688.2022.00666"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1007\/978-3-031-19769-7_38"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/IROS47612.2022.9981506"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/IROS51168.2021.9636080"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1177\/02783649211046285"},{"key":"ref33","article-title":"Learning generalizable robotic reward functions from","author":"Chen","year":"2021","journal-title":"in-the-wild\" human videos,\" arXiv preprint arXiv:2103"},{"key":"ref34","article-title":"Roboclip: One demonstration is enough to learn robot policies","volume":"36","author":"Sontakke","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"year":"2022","author":"Cui","article-title":"From play to policy: Conditional behavior generation from uncurated robot data","key":"ref35"},{"year":"2023","author":"Wang","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","key":"ref36"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/ICDL61372.2024.10644215"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1177\/0278364917743795"},{"key":"ref39","first-page":"1199","article-title":"Viola: Object-centric imitation learning for vision-based robot manipulation","volume-title":"Conference on Robot Learning","author":"Zhu"},{"key":"ref40","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Conference on Robot Learning","author":"Florence"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref42","first-page":"55","article-title":"Graph inverse reinforcement learning from diverse videos","volume-title":"Conference on Robot Learning","author":"Kumar"},{"key":"ref43","first-page":"3536","article-title":"Xskill: Cross embodiment skill discovery","volume-title":"Conference on Robot Learning","author":"Xu"},{"year":"2023","author":"Brohan","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","key":"ref44"},{"year":"2023","author":"Padalkar","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","key":"ref45"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1109\/IROS55552.2023.10341488"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1109\/IROS51168.2021.9636856"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.1109\/ICRA48891.2023.10161143"},{"doi-asserted-by":"publisher","key":"ref49","DOI":"10.1109\/ICRA.2019.8794184"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1109\/ICRA46639.2022.9812360"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1109\/ICRA48891.2023.10160927"},{"year":"2015","author":"Chang","article-title":"Shapenet: An information-rich 3d model repository","key":"ref52"},{"doi-asserted-by":"publisher","key":"ref53","DOI":"10.1109\/CVPR.2019.00100"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.1109\/CVPR42600.2020.01111"},{"doi-asserted-by":"publisher","key":"ref55","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref56","article-title":"Segment anything in high quality","author":"Ke","year":"2023","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref57","DOI":"10.1109\/ICCV.2019.00299"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1109\/CVPR42600.2020.01146"},{"doi-asserted-by":"publisher","key":"ref59","DOI":"10.1109\/tro.2023.3281153"},{"doi-asserted-by":"publisher","key":"ref60","DOI":"10.1109\/CVPR42600.2020.00187"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.1109\/ICCV51070.2023.00371"},{"year":"2023","author":"Wang","article-title":"Wall-e: Embodied robotic waiter load lifting with large language model","key":"ref62"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","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\/10801446.pdf?arnumber=10801446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:57:19Z","timestamp":1735196239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801446","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}