{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T11:16:34Z","timestamp":1762254994937,"version":"3.37.3"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"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":[[2024,7,8]]},"DOI":"10.1109\/icarm62033.2024.10715821","type":"proceedings-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T17:27:32Z","timestamp":1729272452000},"page":"662-667","source":"Crossref","is-referenced-by-count":1,"title":["Learning Instruction-Guided Manipulation Affordance via Large Models for Embodied Robotic Tasks*"],"prefix":"10.1109","author":[{"given":"Dayou","family":"Li","sequence":"first","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China,250061"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenkun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China,250061"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[{"name":"Qilu Hospital of Shandong University,Jinan,China,250012"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan,Beijing,China,100102"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibin","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China,250061"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China,250061"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TSMC.2023.3248324"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/LRA.2021.3062300"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/TRO.2020.2988642"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/IROS.2018.8593986"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICRA40945.2020.9197331"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICCV48922.2021.00674"},{"key":"ref7","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Proc. CoRL","author":"Shridhar"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Int. Conf. Mach. Learn","author":"Radford"},{"key":"ref9","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Proc. CoRL","author":"Zeng"},{"key":"ref10","article-title":"Grounding object relations in languagec-onditioned robotic manipulation with semantic-spatial reasoning","author":"Luo","year":"2023","journal-title":"arXiv preprint arXiv:2303.17919"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref12","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint arXiv:2204.01691"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/IROS55552.2023.10341577"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICRA48891.2023.10161317"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref16","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023","journal-title":"arXiv preprint arXiv:2304.06790"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR52688.2022.01042"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref19","article-title":"Distilling functional rearrangement priors from large models","author":"Zeng","year":"2023","journal-title":"arXiv preprint arXiv:2312.01474"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.15607\/RSS.2023.XIX.027"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR.2016.265"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1145\/2470654.2481301"},{"volume-title":"Proc. Int. Conf. Learn. Represent","author":"Meng","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","key":"ref23"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref25","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Adv. Neural Inform. Process. Syst"},{"key":"ref26","article-title":"Object 3dit: Language-guided 3d-aware image editing","volume":"36","author":"Michel","year":"2024","journal-title":"Adv. Neural Inform. Process. Syst"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICRA48506.2021.9561994"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICRA48891.2023.10161041"},{"volume-title":"in ICRA 2023 Workshop PT4R","author":"Shafiullah","article-title":"Clip-fields: Weakly supervised semantic fields for robotic memory","key":"ref29"},{"key":"ref30","first-page":"405","article-title":"Distilled feature fields enable few-shot language-guided manipulation","volume-title":"Proc. CoRL","author":"Shen"},{"key":"ref31","article-title":"Plan diffuser: Grounding llm planners with diffusion models for robotic manipulation","author":"Sharan","year":"2024","journal-title":"Bridging the Gap between Cognitive Science and Robot Learning in the Real World: Progresses and New Directions"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/ICCV51070.2023.00371"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/WACV51458.2022.00323"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/CVPR52688.2022.01042"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1007\/978-3-031-20080-9_42"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.18653\/v1\/D18-2029"},{"key":"ref37","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2303.05499"}],"event":{"name":"2024 International Conference on Advanced Robotics and Mechatronics (ICARM)","start":{"date-parts":[[2024,7,8]]},"location":"Tokyo, Japan","end":{"date-parts":[[2024,7,10]]}},"container-title":["2024 International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10715684\/10715739\/10715821.pdf?arnumber=10715821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T17:18:20Z","timestamp":1729531100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10715821\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,8]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icarm62033.2024.10715821","relation":{},"subject":[],"published":{"date-parts":[[2024,7,8]]}}}