{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T14:50:48Z","timestamp":1781275848236,"version":"3.54.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Brain Science and Brain-like Intelligence Technology–National Science and Technology Major Project","award":["2025ZD0219400"],"award-info":[{"award-number":["2025ZD0219400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62376009"],"award-info":[{"award-number":["62376009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"PKU-BingJi Joint Laboratory for Artificial Intelligence"},{"name":"Wuhan Major Scientific and Technological Special Program","award":["2025060902020304"],"award-info":[{"award-number":["2025060902020304"]}]},{"name":"Hubei Embodied Intelligence Foundation Model Research and Development Program"},{"name":"National Comprehensive Experimental Base for Governance of Intelligent Society"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/lra.2026.3671701","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:00:15Z","timestamp":1773086415000},"page":"5254-5261","source":"Crossref","is-referenced-by-count":1,"title":["Simultaneous Tactile-Visual Perception for Learning Multimodal Robot Manipulation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5794-7997","authenticated-orcid":false,"given":"Yuyang","family":"Li","sequence":"first","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7110-8097","authenticated-orcid":false,"given":"Yinghan","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3215-7152","authenticated-orcid":false,"given":"Zihang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2696-9346","authenticated-orcid":false,"given":"Puhao","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Institute for General AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4006-1740","authenticated-orcid":false,"given":"Tengyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Institute for General AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1524-7148","authenticated-orcid":false,"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing Institute for General AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7024-1545","authenticated-orcid":false,"given":"Yixin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat8414"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3508134"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/s17122762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3339397"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2017.0052"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3487516"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-01053-3"},{"key":"ref9","article-title":"TacMan-Turbo: Proactive tactile control for robust and efficient articulated object manipulation","author":"Zhao","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981692"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224985"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3111786"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793922"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803400"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246881"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9751-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793959"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191812"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812348"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/RoboSoft55895.2023.10122059"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3593087"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2023.3310918"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3304560"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3521864"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801461"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611186"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2025.3645239"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487126"},{"key":"ref29","article-title":"Vi-TacMan: Articulated object manipulation via vision and touch","volume-title":"Proc. Int. Conf. Robot. Automat.","author":"Cui","year":"2026"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.045"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25075-8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abn0495"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.nanoen.2019.03.013"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.nanoen.2022.107182"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/biorob.2012.6290741"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adl0628"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2977257"},{"issue":"39","key":"ref38","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref39","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Proc. 2nd Conf. Robot Learn.","author":"Kalashnikov","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.065"},{"key":"ref41","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Shridhar","year":"2023"},{"key":"ref42","first-page":"694","article-title":"RVT: Robotic view transformer for 3D object manipulation","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Goyal","year":"2023"},{"key":"ref43","article-title":"Vitamin: Learning contact-rich tasks through robot-free visuo-tactile manipulation interface","author":"Liu","year":"2025"},{"key":"ref44","article-title":"ViTacFormer: Learning cross-modal representation for visuo-tactile dexterous manipulation","author":"Heng","year":"2025"},{"key":"ref45","article-title":"Touch begins where vision ends: Generalizable policies for contact-rich manipulation","volume-title":"Proc. 3rd RSS Workshop Dexterous Manipulation: Learn. Control Diverse Data","author":"Zhao","year":"2025"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3559835"},{"key":"ref49","first-page":"3766","article-title":"Transferable tactile transformers for representation learning across diverse sensors and tasks","volume-title":"Proc. 8th Conf. Robot Learn.","author":"Zhao","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3352969"},{"key":"ref51","first-page":"1488","article-title":"Efficient tactile simulation with differentiability for robotic manipulation","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Xu","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3306670"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127974"},{"key":"ref54","first-page":"2549","article-title":"General in-hand object rotation with vision and touch","volume-title":"Proc. 7th Conf. Robot Learn.","author":"Qi","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref58","first-page":"2024","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref60","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3567247"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_24"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00207"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128816"},{"key":"ref65","article-title":"Taccel: Scaling up vision-based tactile robotics via high-performance GPU simulation","volume-title":"Proc. Adv. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2025"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11400564\/11425767.pdf?arnumber=11425767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:47:08Z","timestamp":1773726428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11425767\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":65,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3671701","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}