{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T03:45:03Z","timestamp":1782963903163,"version":"3.54.5"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T00:00:00Z","timestamp":1768953600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Robotics and Computer-Integrated Manufacturing"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.rcim.2026.103244","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T05:09:14Z","timestamp":1769490554000},"page":"103244","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["VL-GRiP3: A hierarchical pipeline leveraging vision-language models for autonomous robotic 3D grasping"],"prefix":"10.1016","volume":"100","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5229-8920","authenticated-orcid":false,"given":"Mirco","family":"Polonara","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Carbonari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"16","key":"10.1016\/j.rcim.2026.103244_b1","doi-asserted-by":"crossref","first-page":"3602","DOI":"10.3390\/s19163602","article-title":"Bin-picking for planar objects based on a deep learning network: a case study of USB packs","volume":"19","author":"Le","year":"2019","journal-title":"Sensors"},{"key":"10.1016\/j.rcim.2026.103244_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.rcim.2023.102671","article-title":"AttentionVote: A coarse-to-fine voting network of anchor-free 6D pose estimation on point cloud for robotic bin-picking application","volume":"86","author":"Zhuang","year":"2024","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"10.1016\/j.rcim.2026.103244_b3","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/s10514-013-9366-8","article-title":"Learning of grasp selection based on shape-templates","volume":"36","author":"Herzog","year":"2014","journal-title":"Auton. Robots"},{"key":"10.1016\/j.rcim.2026.103244_b4","series-title":"2014 IEEE International Conference on Robotics and Automation","first-page":"1997","article-title":"Fast graspability evaluation on single depth maps for bin picking with general grippers","author":"Domae","year":"2014"},{"key":"10.1016\/j.rcim.2026.103244_b5","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/s43154-020-00021-6","article-title":"A survey on learning-based robotic grasping","volume":"1","author":"Kleeberger","year":"2020","journal-title":"Curr. Robot. Rep."},{"issue":"3","key":"10.1016\/j.rcim.2026.103244_b6","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.robot.2011.07.016","article-title":"An overview of 3D object grasp synthesis algorithms","volume":"60","author":"Sahbani","year":"2012","journal-title":"Robot. Auton. Syst."},{"key":"10.1016\/j.rcim.2026.103244_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.rcim.2021.102229","article-title":"Learning-based object detection and localization for a mobile robot manipulator in SME production","volume":"73","author":"Zhou","year":"2022","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"10.1016\/j.rcim.2026.103244_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.rcim.2023.102564","article-title":"Automation of SME production with a Cobot system powered by learning-based vision","volume":"83","author":"Yang","year":"2023","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"10.1016\/j.rcim.2026.103244_b9","series-title":"Dex-net 2.0: Deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics","author":"Mahler","year":"2017"},{"key":"10.1016\/j.rcim.2026.103244_b10","series-title":"2015 IEEE International Conference on Robotics and Automation","first-page":"1316","article-title":"Real-time grasp detection using convolutional neural networks","author":"Redmon","year":"2015"},{"key":"10.1016\/j.rcim.2026.103244_b11","series-title":"Conference on Robot Learning","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"Kalashnikov","year":"2018"},{"issue":"3","key":"10.1016\/j.rcim.2026.103244_b12","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1007\/s10846-024-02166-4","article-title":"Automatic robot hand-eye calibration enabled by learning-based 3D vision","volume":"110","author":"Li","year":"2024","journal-title":"J. Intell. Robot. Syst."},{"key":"10.1016\/j.rcim.2026.103244_b13","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"7323","article-title":"RT-grasp: Reasoning tuning robotic grasping via multi-modal large language model","author":"Xu","year":"2024"},{"issue":"3","key":"10.1016\/j.rcim.2026.103244_b14","doi-asserted-by":"crossref","first-page":"196","DOI":"10.3390\/machines12030196","article-title":"Introduction of collaborative robotics in the production of automotive parts: A case study","volume":"12","author":"Polonara","year":"2024","journal-title":"Machines"},{"key":"10.1016\/j.rcim.2026.103244_b15","doi-asserted-by":"crossref","DOI":"10.3389\/frobt.2023.1038658","article-title":"Learning-based robotic grasping: A review","volume":"10","author":"Xie","year":"2023","journal-title":"Front. Robot. AI"},{"key":"10.1016\/j.rcim.2026.103244_b16","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.rcim.2026.103244_b17","series-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023"},{"key":"10.1016\/j.rcim.2026.103244_b18","series-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"10.1016\/j.rcim.2026.103244_b19","series-title":"Paligemma: A versatile 3b vlm for transfer","author":"Beyer","year":"2024"},{"key":"10.1016\/j.rcim.2026.103244_b20","series-title":"Vision-language-action models: Concepts, progress, applications and challenges","author":"Sapkota","year":"2025"},{"key":"10.1016\/j.rcim.2026.103244_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.rcim.2025.102978","article-title":"VLM-msgraph: Vision language model-enabled multi-hierarchical scene graph for robotic assembly","volume":"94","author":"Li","year":"2025","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"10.1016\/j.rcim.2026.103244_b22","series-title":"VL-uncertainty: Detecting hallucination in large vision-language model via uncertainty estimation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.rcim.2026.103244_b23","series-title":"A vision-language-action-critic model for robotic real-world reinforcement learning","author":"Zhai","year":"2025"},{"key":"10.1016\/j.rcim.2026.103244_b24","series-title":"Safevla: Towards safety alignment of vision-language-action model via constrained learning","author":"Zhang","year":"2025"},{"key":"10.1016\/j.rcim.2026.103244_b25","series-title":"Instruct2act: Mapping multi-modality instructions to robotic actions with large language model","author":"Huang","year":"2023"},{"issue":"1","key":"10.1016\/j.rcim.2026.103244_b26","doi-asserted-by":"crossref","first-page":"31141","DOI":"10.1038\/s41598-025-17015-z","article-title":"A framework for robotic manipulation tasks based on multiple zero shot models","volume":"15","author":"Li","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.rcim.2026.103244_b27","series-title":"2020 IEEE International Conference on Mechatronics and Automation","first-page":"582","article-title":"Experimental eye-in-hand calibration for industrial mobile manipulators","author":"Zhou","year":"2020"},{"key":"10.1016\/j.rcim.2026.103244_b28","series-title":"Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No. 00CH37065)","first-page":"348","article-title":"Robotic grasping and contact: A review","volume":"1","author":"Bicchi","year":"2000"},{"issue":"2","key":"10.1016\/j.rcim.2026.103244_b29","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1109\/TRO.2013.2289018","article-title":"Data-driven grasp synthesis\u2014a survey","volume":"30","author":"Bohg","year":"2013","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.rcim.2026.103244_b30","series-title":"Closing the loop for robotic grasping: A real-time, generative grasp synthesis approach","author":"Morrison","year":"2018"},{"key":"10.1016\/j.rcim.2026.103244_b31","doi-asserted-by":"crossref","unstructured":"H.-S. Fang, C. Wang, M. Gou, C. Lu, Graspnet-1billion: A large-scale benchmark for general object grasping, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11444\u201311453.","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"10.1016\/j.rcim.2026.103244_b32","series-title":"2022 International Conference on Robotics and Automation","first-page":"1533","article-title":"Transgrasp: A multi-scale hierarchical point transformer for 7-dof grasp detection","author":"Liu","year":"2022"},{"key":"10.1016\/j.rcim.2026.103244_b33","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.rcim.2026.103244_b34","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, pp. 4171\u20134186."},{"key":"10.1016\/j.rcim.2026.103244_b35","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"6","key":"10.1016\/j.rcim.2026.103244_b36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3295748","article-title":"A comprehensive survey of deep learning for image captioning","volume":"51","author":"Hossain","year":"2019","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.rcim.2026.103244_b37","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2425","article-title":"VQA: Visual question answering","author":"Antol","year":"2015"},{"key":"10.1016\/j.rcim.2026.103244_b38","series-title":"Uniter: Learning universal image-text representations","author":"Chen","year":"2019"},{"key":"10.1016\/j.rcim.2026.103244_b39","series-title":"Paligemma 2: A family of versatile vlms for transfer","author":"Steiner","year":"2024"},{"key":"10.1016\/j.rcim.2026.103244_b40","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"12462","article-title":"Physically grounded vision-language models for robotic manipulation","author":"Gao","year":"2024"},{"key":"10.1016\/j.rcim.2026.103244_b41","series-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023"},{"key":"10.1016\/j.rcim.2026.103244_b42","series-title":"Manipulate-anything: Automating real-world robots using vision-language models","author":"Duan","year":"2024"},{"key":"10.1016\/j.rcim.2026.103244_b43","series-title":"2023 IEEE International Conference on Robotics and Automation","first-page":"9493","article-title":"Code as policies: Language model programs for embodied control","author":"Liang","year":"2023"},{"key":"10.1016\/j.rcim.2026.103244_b44","series-title":"Cogact: A foundational vision-language-action model for synergizing cognition and action in robotic manipulation","author":"Li","year":"2024"},{"key":"10.1016\/j.rcim.2026.103244_b45","series-title":"\u03c0_0: A vision-language-action flow model for general robot control","author":"Black","year":"2024"},{"key":"10.1016\/j.rcim.2026.103244_b46","series-title":"Dexbotic: Open-source vision-language-action toolbox","author":"Xie","year":"2025"},{"key":"10.1016\/j.rcim.2026.103244_b47","series-title":"A self-correcting vision-language-action model for fast and slow system manipulation","author":"Li","year":"2024"},{"key":"10.1016\/j.rcim.2026.103244_b48","series-title":"Gr00t n1: An open foundation model for generalist humanoid robots","author":"Bjorck","year":"2025"},{"key":"10.1016\/j.rcim.2026.103244_b49","series-title":"Rt-1: Robotics transformer for real-world control at scale","author":"Brohan","year":"2022"},{"key":"10.1016\/j.rcim.2026.103244_b50","series-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"10.1016\/j.rcim.2026.103244_b51","series-title":"Towards Generalist Robots: Learning Paradigms for Scalable Skill Acquisition@ CoRL2023","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"Vuong","year":"2023"},{"key":"10.1016\/j.rcim.2026.103244_b52","doi-asserted-by":"crossref","unstructured":"S. Huang, Z. Gojcic, M. Usvyatsov, A. Wieser, K. Schindler, Predator: Registration of 3d point clouds with low overlap, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 4267\u20134276.","DOI":"10.1109\/CVPR46437.2021.00425"},{"key":"10.1016\/j.rcim.2026.103244_b53","series-title":"M2t2: Multi-task masked transformer for object-centric pick and place","author":"Yuan","year":"2023"},{"key":"10.1016\/j.rcim.2026.103244_b54","series-title":"International Conference on Machine Learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.rcim.2026.103244_b55","series-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024"},{"key":"10.1016\/j.rcim.2026.103244_b56","series-title":"International Conference on Data Intelligence and Cognitive Informatics","first-page":"529","article-title":"A review on yolov8 and its advancements","author":"Sohan","year":"2024"},{"key":"10.1016\/j.rcim.2026.103244_b57","series-title":"A vision-language-action model with open-world generalization","author":"Intelligence","year":"2025"},{"key":"10.1016\/j.rcim.2026.103244_b58","series-title":"Droid: A large-scale in-the-wild robot manipulation dataset","author":"Khazatsky","year":"2024"}],"container-title":["Robotics and Computer-Integrated Manufacturing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0736584526000232?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0736584526000232?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T03:01:10Z","timestamp":1782961270000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0736584526000232"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":58,"alternative-id":["S0736584526000232"],"URL":"https:\/\/doi.org\/10.1016\/j.rcim.2026.103244","relation":{},"ISSN":["0736-5845"],"issn-type":[{"value":"0736-5845","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"VL-GRiP3: A hierarchical pipeline leveraging vision-language models for autonomous robotic 3D grasping","name":"articletitle","label":"Article Title"},{"value":"Robotics and Computer-Integrated Manufacturing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.rcim.2026.103244","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"103244"}}