{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:09:29Z","timestamp":1774022969793,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20230924"],"award-info":[{"award-number":["GZC20230924"]}]},{"name":"Hubei Engineering Research Center for Intelligent Detection and Identification of Complex Parts","award":["IDICP-KF-2024-03"],"award-info":[{"award-number":["IDICP-KF-2024-03"]}]},{"DOI":"10.13039\/100017938","name":"Hubei Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2024AFB245"],"award-info":[{"award-number":["2024AFB245"]}],"id":[{"id":"10.13039\/100017938","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203341"],"award-info":[{"award-number":["62203341"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017938","name":"Hubei Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2024AFB614"],"award-info":[{"award-number":["2024AFB614"]}],"id":[{"id":"10.13039\/100017938","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3550360","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T13:52:03Z","timestamp":1741701123000},"page":"13073-13086","source":"Crossref","is-referenced-by-count":9,"title":["Integrating With Multimodal Information for Enhancing Robotic Grasping With Vision-Language Models"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6547-646X","authenticated-orcid":false,"given":"Zhou","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science, Central China Normal University, Wuhan, China"}]},{"given":"Dongyuan","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Central China Normal University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1637-0092","authenticated-orcid":false,"given":"Yizi","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Cartography and Geoinformation, ETH Z&#x00FC;rich, Z&#x00FC;rich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9480-5875","authenticated-orcid":false,"given":"Jing","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Automation, Wuhan University of Technology, Wuhan, China"}]},{"given":"Yanjun","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Marine Equipment, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5132-9602","authenticated-orcid":false,"given":"Panfeng","family":"Huang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Aerospace Flight Dynamics and the Research Center for Intelligent Robotics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5255-5559","authenticated-orcid":false,"given":"Chenguang","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Liverpool, Liverpool, U.K."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3253249"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3330664"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270745"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3264759"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2023.3264650"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594159"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhac293"},{"key":"ref8","article-title":"A survey of attacks on large vision-language models: Resources, advances, and future trends","author":"Liu","year":"2024","journal-title":"arXiv:2407.07403"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SII58957.2024.10417178"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915602060"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460699"},{"key":"ref13","first-page":"1829","article-title":"Few-shot object grounding and mapping for natural language robot instruction following","volume-title":"Proc. Conf. Robot Learn.","author":"Blukis"},{"key":"ref14","first-page":"1450","article-title":"Language-guided robot grasping: CLIP-based referring grasp synthesis in clutter","volume-title":"Proc. Conf. Robot Learn.","author":"Tziafas"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561802"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3261745"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3272571"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974391"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295296"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3359553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812360"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610543"},{"key":"ref24","article-title":"Target-oriented object grasping via multimodal human guidance","author":"Xie","year":"2024","journal-title":"arXiv:2408.11138"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3286071"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3436334"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01695"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342331"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104271"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jai.2024.12.003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3446625"},{"key":"ref33","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref34","first-page":"25081","article-title":"EmbodiedGPT: Vision-language pre-training via embodied chain of thought","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mu"},{"key":"ref35","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Driess"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00648"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802256"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-014-9402-3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919859066"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3413164"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561994"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"issue":"8","key":"ref48","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref50","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561398"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793917"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00891"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611277"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852777"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145064"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3214196"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161149"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10921661.pdf?arnumber=10921661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:10:19Z","timestamp":1773951019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10921661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3550360","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}