{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T06:30:50Z","timestamp":1772001050450,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"China's National Natural Science Fund for Key International Collaboration","award":["62120106005"],"award-info":[{"award-number":["62120106005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/lra.2025.3541334","type":"journal-article","created":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T18:24:00Z","timestamp":1739384640000},"page":"3422-3429","source":"Crossref","is-referenced-by-count":6,"title":["Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2972-0863","authenticated-orcid":false,"given":"Guokang","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2667-8843","authenticated-orcid":false,"given":"Hang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Shuyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9816-0103","authenticated-orcid":false,"given":"Di","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7349-5871","authenticated-orcid":false,"given":"Yanhong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4042-6044","authenticated-orcid":false,"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140817"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01337"},{"key":"ref3","article-title":"Learning to look by self-prediction","author":"Grimes","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref4","first-page":"2784","article-title":"Stabilizing off-policy deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cetin","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1068\/p2935"},{"key":"ref6","first-page":"10316","article-title":"Active vision reinforcement learning under limited visual observability","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 36: Annu. Conf. Neural Inf. Process. Syst. 2023","volume":"36","author":"Shang","year":"2023"},{"key":"ref7","article-title":"Active perception and representation for robotic manipulation","author":"Zaky","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.040"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00221-010-2241-3"},{"key":"ref10","first-page":"422","article-title":"Reinforcement learning of active vision for manipulating objects under occlusions","volume-title":"2nd Annu. Conf. Robot Learn.","author":"Cheng","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01717"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793805"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197185"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/bf00133571"},{"key":"ref16","first-page":"13086","article-title":"SEAL: Self-supervised embodied active learning using exploration and 3D consistency","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 34: Annu. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Chaplot","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01547"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3157028"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01555"},{"key":"ref20","first-page":"2849","article-title":"Affordance-driven next-best-view planning for robotic grasping","volume-title":"Proc. Conf. Robot Learn.","volume":"229","author":"Zhang","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystemseng.2024.08.002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610397"},{"key":"ref23","article-title":"Active vision might be all you need: Exploring active vision in bimanual robotic manipulation","author":"Chuang","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10341809"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16440-8_61"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3161829"},{"key":"ref28","first-page":"64318","article-title":"Occ3D: A large-scale 3 D occupancy prediction benchmark for autonomous driving","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 36: Annu. Conf. Neural Inf. Process. Syst.","volume":"36","author":"Tian","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref30","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar","year":"2022"},{"key":"ref31","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jaegle","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610241"},{"key":"ref33","first-page":"477","article-title":"Learning 6-DoF grasping and pick-place using attention focus","volume-title":"Proc. 2nd Annu. Conf. Robot Learn.","author":"Gualtieri","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801388"},{"key":"ref35","first-page":"424","article-title":"3 D U-Net: Learning dense volumetric segmentation from sparse annotation","volume-title":"Proc. Med. Image Comput. Comput.-Assist. Interv.","author":"iek","year":"2016"},{"key":"ref36","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Sunehag","year":"2018"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10893718\/10883018.pdf?arnumber=10883018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T06:13:10Z","timestamp":1740809590000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10883018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":36,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3541334","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}