{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:41:21Z","timestamp":1771922481595,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1109\/robio66223.2025.11375938","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:43:52Z","timestamp":1771879432000},"page":"1227-1232","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal-Driven Intelligent Grasping Decision System: A Semantic-Visual-Physical End-to-End Collaborative Architecture"],"prefix":"10.1109","author":[{"given":"Songtao","family":"Ding","sequence":"first","affiliation":[{"name":"Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000"}]},{"given":"Zhen","family":"Fang","sequence":"additional","affiliation":[{"name":"Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000"}]},{"given":"Hongyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000"}]},{"given":"Mengsen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.106716"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981799"},{"key":"ref3","first-page":"291","article-title":"Learning a visuomotor controller for real world robotic grasping using simulated depth images","volume-title":"Conference on robot learning","author":"Viereck","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-024-02321-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611417"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning. PMLR","author":"Radford","year":"2021"},{"key":"ref7","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref8","volume-title":"OpenAI. Gpt-4o: Openai\u2019s multimodal vision-language system","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01146"},{"key":"ref11","first-page":"453","article-title":"A geometrical approach to planning manipulation tasks. the case of discrete placements and grasps[C]","volume-title":"The fifth international symposium on Robotics research","author":"Alami","year":"2018"},{"key":"ref12","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on robot learning","author":"Kalashnikov","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01566"},{"key":"ref15","article-title":"Thinkgrasp: A vision-language system for strategic part grasping in clutter[J]","author":"Qian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"ref17","article-title":"Bidirectional language models are also few-shot learners","volume-title":"International Conference on Learning Representations (ICLR)","author":"Patel","year":"2023"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","volume":"139","author":"Radford","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341379"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320012"},{"key":"ref22","article-title":"Do as i can, not as i say: Grounding language in robotic affordances[J]","author":"Ahn","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref24","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control[J]","author":"Brohan","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models[J]","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Chengdu, China","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,7]]}},"container-title":["2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373909\/11375854\/11375938.pdf?arnumber=11375938","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:36:31Z","timestamp":1771918591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11375938\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/robio66223.2025.11375938","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}