{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T20:48:57Z","timestamp":1782334137641,"version":"3.54.5"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Harbin Institute of Technology, Shenzhen, China"},{"name":"Pengcheng Laboratory, Shenzhen, China"},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2024ZD01NL00104"],"award-info":[{"award-number":["2024ZD01NL00104"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"name":"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 Systems Journal"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/jsyst.2026.3680039","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T19:53:21Z","timestamp":1778183601000},"page":"427-435","source":"Crossref","is-referenced-by-count":0,"title":["Active Perception Strategies for Multimodal Integration and Latent Information Reasoning in Robotic Systems"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6270-7086","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2336-6606","authenticated-orcid":false,"given":"Jiankun","family":"Yang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7161-1146","authenticated-orcid":false,"given":"Haibo","family":"Lu","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8070-802X","authenticated-orcid":false,"given":"Wen","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","first-page":"32400","article-title":"SPHINX-X: Scaling data and parameters for a family of multi-modal large language models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Liu","year":"2024"},{"key":"ref3","first-page":"287","article-title":"Do as I can and not as I say: Grounding language in robotic affordances","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Ichter","year":"2023"},{"key":"ref4","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. 8th Conf. Robot Learn.","author":"Kim","year":"2025"},{"key":"ref5","article-title":"RoboMamba: Multimodal state space model for efficient robot reasoning and manipulation","volume-title":"Proc. 38th Int. Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1910"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342363"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2025.3574943"},{"key":"ref9","first-page":"894","article-title":"CLIPort: What and where pathways for robotic manipulation","volume-title":"Proc. Conf. Robot Learn. (CoRL)","volume":"164","author":"Shridhar","year":"2022"},{"key":"ref10","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Driess","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-021-00018-1"},{"key":"ref12","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref13","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2023.3237225"},{"key":"ref15","first-page":"18378","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2024","author":"Zhu","year":"2024"},{"key":"ref16","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref18","first-page":"25081","article-title":"EmbodiedGPT: Vision-language pre-training via embodied chain of thought","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Mu","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2020.3026879"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3441495"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref23","first-page":"492","article-title":"LM-Nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. Conf. Robot Learn.","author":"Shah","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104256"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801993"},{"key":"ref26","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. Conf. Robot Learn. (CoRL)","volume":"229","author":"Huang","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561479"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3055194"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2025.3603993"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967584"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981510"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3329370"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3531816"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3483037"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981578"}],"container-title":["IEEE Systems Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4267003\/11570649\/11511869.pdf?arnumber=11511869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:50:03Z","timestamp":1782330603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11511869\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":36,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jsyst.2026.3680039","relation":{},"ISSN":["1932-8184","1937-9234","2373-7816"],"issn-type":[{"value":"1932-8184","type":"print"},{"value":"1937-9234","type":"electronic"},{"value":"2373-7816","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}