{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T08:09:49Z","timestamp":1769155789937,"version":"3.49.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T00:00:00Z","timestamp":1749686400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T00:00:00Z","timestamp":1749686400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"the Basic Science (Natural Science) General Program of Colleges and Universities in Jiangsu Province","award":["23KJB460031"],"award-info":[{"award-number":["23KJB460031"]}]},{"name":"the Natural Science Foundation of Jiangsu Province for Young Scholars","award":["BK20230173"],"award-info":[{"award-number":["BK20230173"]}]},{"name":"the Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment & Technology","award":["FM-202304"],"award-info":[{"award-number":["FM-202304"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s40747-025-01981-y","type":"journal-article","created":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T04:53:40Z","timestamp":1749704020000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Command-driven semantic robotic grasping towards user-specified tasks"],"prefix":"10.1007","volume":"11","author":[{"given":"Qing","family":"Lyu","sequence":"first","affiliation":[]},{"given":"Qingwen","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Xiaoyan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Qiuju","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,12]]},"reference":[{"key":"1981_CR1","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1177\/01423312221142564","volume":"45","author":"S Guan","year":"2023","unstructured":"Guan S, Zhuang Z, Tao H, Chen Y, Stojanovic V, Paszke W (2023) Feedback-aided PD-type iterative learning control for time-varying systems with non-uniform trial lengths. Trans Inst Meas Control 45:2015\u20132026","journal-title":"Trans Inst Meas Control"},{"key":"1981_CR2","doi-asserted-by":"publisher","first-page":"3086","DOI":"10.1109\/TASE.2024.3389020","volume":"22","author":"Z Zhang","year":"2025","unstructured":"Zhang Z, Zhang K, Xie X, Stojanovic V (2025) ADP-based prescribed-time control for nonlinear time-varying delay systems with uncertain parameters. IEEE Trans Autom Sci Eng 22:3086\u20133096","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"1981_CR3","unstructured":"Gemini Team R, Anil S, Borgeaud J-B, Alayrac J, Yu R, Soricut J, Schalkwyk AM, Dai A, Hauth K, Millican et al (2023) Gemini: a family of highly capable multimodal models, arXiv preprint arXiv:2312.11805"},{"key":"1981_CR4","unstructured":"Liu A, Feng B, Xue B, Wang B, Wu B, Lu C, Zhao C, Deng C, Zhang C, Ruan C, et al., (2024)Deepseek-v3 technical report, arXiv preprint arXiv:2412.19437,"},{"key":"1981_CR5","first-page":"705","volume":"4","author":"I Lenz","year":"2013","unstructured":"Lenz I, Lee H, Saxena A (2013) Deep Learning for Detecting Robotic Grasps. Int J Robot Res 4:705\u2013724","journal-title":"Int J Robot Res"},{"key":"1981_CR6","doi-asserted-by":"publisher","first-page":"26407","DOI":"10.1109\/JSEN.2024.3424218","volume":"24","author":"Y Xu","year":"2024","unstructured":"Xu Y, Chen Z, Deng C, Wang S, Wang J (2024) LCDL: toward dynamic localization for autonomous landing of unmanned aerial vehicle based on LiDAR\u2013camera fusion. IEEE Sens J 24:26407\u201326415","journal-title":"IEEE Sens J"},{"key":"1981_CR7","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1016\/j.isatra.2024.09.008","volume":"155","author":"Z Chen","year":"2024","unstructured":"Chen Z, Zhan G, Jiang Z, Zhang W, Rao Z, Wang H, Li J (2024) Adaptive impedance control for docking robot via Stewart parallel mechanism. ISA Trans 155:361\u2013372","journal-title":"ISA Trans"},{"key":"1981_CR8","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1177\/0278364917735594","volume":"36","author":"A Ten Pas","year":"2017","unstructured":"Ten Pas A, Gualtieri M, Saenko K, Platt R (2017) Grasp pose detection in point clouds. Int J Robot Res 36:1455\u20131473","journal-title":"Int J Robot Res"},{"key":"1981_CR9","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MRA.2015.2448951","volume":"22","author":"B Calli","year":"2015","unstructured":"Calli B, Walsman A, Singh A, Srinivasa S, Abbeel P, Dollar AM (2015) Benchmarking in manipulation research: using the Yale-CMU-Berkeley object and model set. IEEE Robot Autom Mag 22:36\u201352","journal-title":"IEEE Robot Autom Mag"},{"key":"1981_CR10","first-page":"2637","volume":"2019","author":"H Wang","year":"2019","unstructured":"Wang H, Sridhar S, Huang J, Valentin J, Song S, Guibas LJ (2019) Normalized object coordinate space for category-level 6D object pose and size estimation. IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR) 2019:2637\u20132646","journal-title":"IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"1981_CR11","first-page":"3511","volume":"2018","author":"A Depierre","year":"2018","unstructured":"Depierre A, Dellandr\u00e9a E, Chen L (2018) Jacquard: a large scale dataset for robotic grasp detection. IEEE\/RSJ Int Conf Intell Robot Syst (IROS) 2018:3511\u20133516","journal-title":"IEEE\/RSJ Int Conf Intell Robot Syst (IROS)"},{"key":"1981_CR12","first-page":"11444","volume":"2020","author":"H-S Fang","year":"2020","unstructured":"Fang H-S, Wang C, Gou M, Lu C (2020) Graspnet-1billion: A large-scale benchmark for general object grasping, in. IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR) 2020:11444\u201311453","journal-title":"IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"1981_CR13","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1177\/0278364919859066","volume":"39","author":"D Morrison","year":"2020","unstructured":"Morrison D, Corke P, Leitner J (2020) Learning robust, real-time, reactive robotic grasping. Int J Robot Res 39:183\u2013201","journal-title":"Int J Robot Res"},{"key":"1981_CR14","first-page":"9626","volume":"2020","author":"S Kumra","year":"2020","unstructured":"Kumra S, Joshi S, Sahin F (2020) Antipodal robotic grasping using generative residual convolutional neural network. IEEE\/RSJ Int Conf Intell Robots Syst (IROS) 2020:9626\u20139633","journal-title":"IEEE\/RSJ Int Conf Intell Robots Syst (IROS)"},{"key":"1981_CR15","doi-asserted-by":"publisher","first-page":"8170","DOI":"10.1109\/LRA.2022.3187261","volume":"7","author":"S Wang","year":"2022","unstructured":"Wang S, Zhou Z, Kan Z (2022) When transformer meets robotic grasping: Exploits context for efficient grasp detection. IEEE Robot Auto Lett 7:8170\u20138177","journal-title":"IEEE Robot Auto Lett"},{"key":"1981_CR16","unstructured":"Huang W, Abbeel P, Pathak D, Mordatch I (2022) Language models as zero-shot planners: Extracting actionable knowledge for embodied agents, in: International Conference on Machine Learning (ICML), 9118-9147"},{"key":"1981_CR17","doi-asserted-by":"crossref","unstructured":"Nazarczuk M, Mikolajczyk K, (2020) V2A-Vision to Action: Learning robotic arm actions based on vision and language, in: Proceedings of the Asian Conference on Computer Vision (ACCV), 721-736","DOI":"10.1007\/978-3-030-69535-4_44"},{"key":"1981_CR18","doi-asserted-by":"crossref","unstructured":"Liu P, Orru Y, Paxton C, Shafiullah NMM, Pinto L (2024) Ok-robot: What really matters in integrating open-knowledge models for robotics, arXiv preprint arXiv:2401.12202,","DOI":"10.15607\/RSS.2024.XX.091"},{"key":"1981_CR19","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J (2021) Learning transferable visual models from natural language supervision. International Conference on Machine Learning (ICML) 8748\u20138763"},{"key":"1981_CR20","first-page":"14432","volume":"2024","author":"X Chen","year":"2024","unstructured":"Chen X, Djolonga J, Padlewski P, Mustafa B, Changpinyo S, Wu J, Ruiz CR, Goodman S, Wang X, Tay Y (2024) On scaling up a multilingual vision and language model. IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR) 2024:14432\u201314444","journal-title":"IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"1981_CR21","unstructured":"Driess D, Xia F, Sajjadi MS, Lynch C, Chowdhery A, Ichter B, Wahid A, Tompson J, Vuong Q, Yu T (2023) Palm-e: an embodied multimodal language model. International Conference on Machine Learning (PMLR) 8469\u20138488"},{"key":"1981_CR22","unstructured":"Zitkovich B, Yu T, Xu S, Xu P, Xiao T, Xia F, Wu J, Wohlhart P, Welker S, A. (2023) Wahid, Rt-2: Vision-language-action models transfer web knowledge to robotic control. Conference on Robot Learning (CoRL) 2165\u20132183"},{"key":"1981_CR23","first-page":"14030","volume":"2024","author":"AD Vuong","year":"2024","unstructured":"Vuong AD, Vu MN, Le H, Huang B, Binh HTT, Vo T, Kugi A, Nguyen A (2024) Grasp-anything: large-scale grasp dataset from foundation models. IEEE Int Conf Robot Auto (ICRA) 2024:14030\u201314037","journal-title":"IEEE Int Conf Robot Auto (ICRA)"},{"key":"1981_CR24","doi-asserted-by":"crossref","unstructured":"Vuong AD, Vu MN, Huang B, Nguyen N, Le H, Vo T, Nguyen A (2024) Language-driven grasp detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 17902\u201317912","DOI":"10.1109\/CVPR52733.2024.01695"},{"key":"1981_CR25","unstructured":"Jin S, Xu J, Lei Y, Zhang L (2024) Reasoning Grasping via Multimodal Large Language Model, arXiv preprint arXiv:2402.06798,"},{"key":"1981_CR26","doi-asserted-by":"crossref","unstructured":"Xu K, Zhao S, Zhou Z, Li Z, Pi H, Zhu Y, Wang Y, Xiong R (2023) A joint modeling of vision-language-action for target-oriented grasping in clutter, in. IEEE Int Conf Robot Auto (ICRA) 2023:11597\u201311604","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"1981_CR27","doi-asserted-by":"publisher","first-page":"7551","DOI":"10.1109\/LRA.2023.3320012","volume":"8","author":"C Tang","year":"2023","unstructured":"Tang C, Huang D, Ge W, Liu W, Zhang H (2023) Graspgpt: leveraging semantic knowledge from a large language model for task-oriented grasping. IEEE Robot Auto Lett 8:7551\u20137558","journal-title":"IEEE Robot Auto Lett"},{"key":"1981_CR28","unstructured":"Mirjalili R, Krawez M, Silenzi S, Blei Y, Burgard W (2023) Lan-grasp: Using large language models for semantic object grasping, arXiv preprint arXiv:2310.05239,"},{"key":"1981_CR29","first-page":"976","volume":"2023","author":"Y Lu","year":"2023","unstructured":"Lu Y, Fan Y, Deng B, Liu F, Li Y, Wang S (2023) Vl-grasp: a 6-dof interactive grasp policy for language-oriented objects in cluttered indoor scenes, in. IEEE\/RSJ Int Conf Intell Robots Syst (IROS) 2023:976\u2013983","journal-title":"IEEE\/RSJ Int Conf Intell Robots Syst (IROS)"},{"key":"1981_CR30","doi-asserted-by":"crossref","unstructured":"Pham K, Kafle K, Lin Z, Ding Z, Cohen S, Tran Q, Shrivastava A (2021) Learning to predict visual attributes in the wild. IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR) 2021:13018\u201313028","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"1981_CR31","first-page":"1837","volume":"2017","author":"Y Li","year":"2017","unstructured":"Li Y, Song Y, Luo J (2017) Improving Pairwise Ranking for Multi-label Image Classification. IEEE Conf Comput Vis Pattern Recognit (CVPR) 2017:1837\u20131845","journal-title":"IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"1981_CR32","first-page":"5172","volume":"2019","author":"ZM Chen","year":"2019","unstructured":"Chen ZM, Wei XS, Wang P, Guo Y (2019) Multi-label image recognition with graph convolutional networks. IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR) 2019:5172\u20135181","journal-title":"IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"1981_CR33","doi-asserted-by":"crossref","unstructured":"Sarafianos N, Xu X, Kakadiaris IA (2018) Deep Imbalanced Attribute Classification Using Visual Attention Aggregation. Proceedings of the European conference on computer vision (ECCV) 708\u2013725","DOI":"10.1007\/978-3-030-01252-6_42"},{"key":"1981_CR34","first-page":"3304","volume":"2011","author":"J Yun","year":"2011","unstructured":"Yun J, Moseson S, Saxena A (2011) Efficient grasping from RGBD images: learning using a new rectangle representation. IEEE Int Conf Robot Auto (ICRA) 2011:3304\u20133311","journal-title":"IEEE Int Conf Robot Auto (ICRA)"},{"key":"1981_CR35","doi-asserted-by":"publisher","first-page":"3355","DOI":"10.1109\/LRA.2018.2852777","volume":"3","author":"FJ Chu","year":"2018","unstructured":"Chu FJ, Xu R, Vela PA (2018) Real-world multiobject, multigrasp detection. IEEE Robot Auto Lett 3:3355\u20133362","journal-title":"IEEE Robot Auto Lett"},{"key":"1981_CR36","first-page":"7223","volume":"2018","author":"X Zhou","year":"2018","unstructured":"Zhou X, Lan X, Zhang H, Tian Z, Zhang Y, Zheng N (2018) Fully Convolutional Grasp Detection Network with Oriented Anchor Box, in. IEEE\/RSJ Int Conf Intell Robots Syst (IROS) 2018:7223\u20137230","journal-title":"IEEE\/RSJ Int Conf Intell Robots Syst (IROS)"},{"key":"1981_CR37","doi-asserted-by":"crossref","unstructured":"Zhou Z, Zhang X, Ran L, Han Y, Chu H (2023) DSC-GraspNet: A Lightweight Convolutional Neural Network for Robotic Grasp Detection, in: 2023 9th International Conference on Virtual Reality (ICVR), 226-232","DOI":"10.1109\/ICVR57957.2023.10169448"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01981-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-01981-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01981-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T19:20:07Z","timestamp":1757186407000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-01981-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,12]]},"references-count":37,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["1981"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-01981-y","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,12]]},"assertion":[{"value":"24 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}],"article-number":"334"}}