{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:01:09Z","timestamp":1782759669522,"version":"3.54.5"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246329","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"14931-14938","source":"Crossref","is-referenced-by-count":1,"title":["VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility"],"prefix":"10.1109","author":[{"given":"Yitian","family":"Shi","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Wen","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanqi","family":"Chen","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edgar","family":"Welte","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunyu","family":"Peng","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rainer","family":"Stiefelhagen","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rania","family":"Rayyes","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3280597"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2023.3328964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197318"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160842"},{"key":"ref7","article-title":"Volumetric grasping network: Real-time 6 dof grasp detection in clutter","volume-title":"CoRL","author":"Breyer"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3544083"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981472"},{"key":"ref10","article-title":"Affordance-driven next-best-view planning for robotic grasping","volume-title":"CoRL","author":"Zhang"},{"key":"ref11","article-title":"Active perception for grasp detection via neural graspness field","author":"Ma","year":"2024","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref13","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128811"},{"key":"ref16","article-title":"Towards open-world grasping with large vision-language models","volume-title":"CoRL","author":"Tziafas"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801718"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids65713.2025.11203035"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127888"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794435"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793805"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9615-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/027836402128964099"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3555149\/mm1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610617"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340916"},{"key":"ref29","article-title":"Part-slip: Low-shot part segmentation for 3d point clouds via pretrained image-language models","volume-title":"CVPR","author":"Liu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.120"},{"key":"ref31","article-title":"Reasoning grasping via multi-modal large language model","author":"Jin","year":"2024"},{"key":"ref32","article-title":"Smart: Self-supervised multi-task pretraining with control transformers","author":"Sun","year":"2023"},{"key":"ref33","first-page":"416","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"CoRL","author":"Radosavovic"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1177\/02783649241281508","article-title":"Foundation models in robotics: Applications, challenges, and the future","volume-title":"CoRR","author":"Firoozi"},{"key":"ref35","article-title":"Toward general-purpose robots via foundation models: A survey and meta-analysis","volume-title":"CoRR","author":"Hu"},{"key":"ref36","article-title":"Know where you\u2019re uncertain when planning with multimodal foundation models: A formal framework","author":"Bhatt","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3542418"},{"key":"ref38","article-title":"Thinkgrasp: A vision-language system for strategic part grasping in clutter","volume-title":"2nd CoRL Workshop on Learning Effective Abstractions for Planning","author":"Qian"},{"key":"ref39","article-title":"Ap-vlm: Active perception enabled by vision-language models","author":"Sripada","year":"2024"},{"key":"ref40","article-title":"On the bounding boxes obtained by principal component analysis","author":"Dimitrov","year":"2006","journal-title":"EuroCG"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.552"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610125"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/63.1.203"},{"issue":"34","key":"ref44","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","volume":"96","author":"Ester","year":"1996","journal-title":"kdd"},{"key":"ref45","article-title":"Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions","volume-title":"ICLR","author":"Charpentier"},{"key":"ref46","article-title":"Pointnext: Revisiting pointnet++ with improved training and scaling strategies","author":"Qian","year":"2022","journal-title":"NeurIPS"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246329.pdf?arnumber=11246329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:10:58Z","timestamp":1765519858000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246329\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246329","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}