{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:15:28Z","timestamp":1765520128397,"version":"3.48.0"},"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":0,"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"}]},{"given":"Di","family":"Wen","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}]},{"given":"Guanqi","family":"Chen","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}]},{"given":"Edgar","family":"Welte","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}]},{"given":"Sheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}]},{"given":"Kunyu","family":"Peng","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}]},{"given":"Rainer","family":"Stiefelhagen","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}]},{"given":"Rania","family":"Rayyes","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TRO.2023.3280597"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/CVPR42600.2020.01146"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/tase.2023.3328964"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.15607\/RSS.2017.XIII.058"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICRA40945.2020.9197318"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICRA48891.2023.10160842"},{"volume-title":"CoRL","author":"Breyer","article-title":"Volumetric grasping network: Real-time 6 dof grasp detection in clutter","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/LRA.2025.3544083"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/IROS47612.2022.9981472"},{"volume-title":"CoRL","author":"Zhang","article-title":"Affordance-driven next-best-view planning for robotic grasping","key":"ref10"},{"key":"ref11","article-title":"Active perception for grasp detection via neural graspness field","author":"Ma","year":"2024","journal-title":"NeurIPS"},{"year":"2025","author":"Bai","article-title":"Qwen2. 5-vl technical report","key":"ref12"},{"year":"2024","author":"Ravi","article-title":"Sam 2: Segment anything in images and videos","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1007\/978-3-031-72970-6_3"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/icra55743.2025.11128811"},{"volume-title":"CoRL","author":"Tziafas","article-title":"Towards open-world grasping with large vision-language models","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/IROS58592.2024.10801718"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/Humanoids65713.2025.11203035"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/icra55743.2025.11127888"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICRA48506.2021.9561877"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICRA.2019.8794435"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.15607\/RSS.2021.XVII.024"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ICRA.2019.8793805"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1007\/s10514-017-9615-3"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1177\/027836402128964099"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/lra.2025.3555149\/mm1"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICRA57147.2024.10610617"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/IROS45743.2020.9340916"},{"volume-title":"CVPR","author":"Liu","article-title":"Part-slip: Low-shot part segmentation for 3d point clouds via pretrained image-language models","key":"ref29"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.18653\/v1\/2022.acl-long.120"},{"year":"2024","author":"Jin","article-title":"Reasoning grasping via multi-modal large language model","key":"ref31"},{"year":"2023","author":"Sun","article-title":"Smart: Self-supervised multi-task pretraining with control transformers","key":"ref32"},{"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"},{"volume-title":"CoRR","author":"Hu","article-title":"Toward general-purpose robots via foundation models: A survey and meta-analysis","key":"ref35"},{"year":"2024","author":"Bhatt","article-title":"Know where you\u2019re uncertain when planning with multimodal foundation models: A formal framework","key":"ref36"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/TASE.2025.3542418"},{"volume-title":"2nd CoRL Workshop on Learning Effective Abstractions for Planning","author":"Qian","article-title":"Thinkgrasp: A vision-language system for strategic part grasping in clutter","key":"ref38"},{"year":"2024","author":"Sripada","article-title":"Ap-vlm: Active perception enabled by vision-language models","key":"ref39"},{"key":"ref40","article-title":"On the bounding boxes obtained by principal component analysis","author":"Dimitrov","year":"2006","journal-title":"EuroCG"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.18653\/v1\/2023.findings-emnlp.552"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1109\/ICRA57147.2024.10610125"},{"doi-asserted-by":"publisher","key":"ref43","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"},{"volume-title":"ICLR","author":"Charpentier","article-title":"Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions","key":"ref45"},{"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)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","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]]}}}