{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T06:00:56Z","timestamp":1777874456593,"version":"3.51.4"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276028"],"award-info":[{"award-number":["62276028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hebei Provincial Central Government-Guided Local Science and Technology","award":["236Z1811G"],"award-info":[{"award-number":["236Z1811G"]}]},{"name":"Innovation Capability Improvement Plan of Hebei Province","award":["22567626H"],"award-info":[{"award-number":["22567626H"]}]},{"DOI":"10.13039\/501100008238","name":"Hebei Provincial Department of Science and Technology","doi-asserted-by":"publisher","award":["F202103079"],"award-info":[{"award-number":["F202103079"]}],"id":[{"id":"10.13039\/501100008238","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hebei Province Yanzhao Golden Terrace Talent Gathering Program","award":["C2025005"],"award-info":[{"award-number":["C2025005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/lra.2026.3683592","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:48:05Z","timestamp":1777060085000},"page":"7086-7093","source":"Crossref","is-referenced-by-count":0,"title":["PGCSPose: Physics-Constrained Generation and Causal Semantic Fusion for Robust In-Hand Pose Estimation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1228-2757","authenticated-orcid":false,"given":"Peiliang","family":"Wu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence (School of Software), Yanshan University, Qinhuangdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7631-2459","authenticated-orcid":false,"given":"Yao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence (School of Software), Yanshan University, Qinhuangdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5133-7525","authenticated-orcid":false,"given":"Mingyue","family":"Niu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence (School of Software), Yanshan University, Qinhuangdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7683-2776","authenticated-orcid":false,"given":"Wenbai","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing Information Science and Technology University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3437-4265","authenticated-orcid":false,"given":"Guowei","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing Information Science and Technology University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341688"},{"key":"ref2","first-page":"49921","article-title":"VinT-6D: A large-scale object-in-hand dataset from vision, touch and proprioception","volume-title":"Proc. Mach. Learn. Res.","author":"Wan","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2977257"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11245928"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127966"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139171731"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref10","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Mach. Learn. Res.","volume":"229","author":"Brohan","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref12","volume-title":"Elements of Causal Inference: Foundations and Learning Algorithms","author":"Peters","year":"2017"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref14","first-page":"2021","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref15","first-page":"10511","article-title":"Touch-GS: Visual-tactile supervised 3D Gaussian splatting","volume-title":"Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst.","author":"Aiden","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852779"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2959445"},{"key":"ref18","first-page":"3766","article-title":"Transferable tactile transformers for representation learning across diverse sensors and tasks","volume-title":"Proc. Mach. Learn. Res.","volume":"270","author":"Zhao","year":"2024"},{"key":"ref19","article-title":"UniT: Unified tactile representation for robot learning","author":"Xu","year":"2024"},{"key":"ref20","article-title":"ViTaPEs: Visuotactile position encodings for cross-modal alignment in multimodal transformers","author":"Lygerakis","year":"2025"},{"key":"ref21","first-page":"5418","article-title":"Dense tactile force estimation using GelSlim and inverse FEM","volume-title":"Proc. IEEE Int. Conf. Robot. Automat.","author":"Wang","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00850"},{"key":"ref23","first-page":"319","article-title":"MidasTouch: Monte-Carlo inference over distributions across sliding touch","volume-title":"Proc. Mach. Learn. Res.","volume":"205","author":"Suresh","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01086"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02505"},{"key":"ref27","first-page":"11698","article-title":"Causal confusion in imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Haan","year":"2019"},{"key":"ref28","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conf. Robot Learn., PMLR","author":"Brohan","year":"2023"},{"key":"ref29","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Mach. Learn. Res.","volume":"202","author":"Driess","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref31","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Mach. Learn. Res.","volume":"139","author":"Jia","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"70","key":"ref35","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128495"},{"key":"ref38","article-title":"In-Hand object pose estimation via visual-tactile fusion","author":"Nonnengieer","year":"2025"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11481819\/11480997.pdf?arnumber=11480997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:49:23Z","timestamp":1777578563000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11480997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":38,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3683592","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}