{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T20:49:22Z","timestamp":1781556562527,"version":"3.54.5"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100019827","name":"Meta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019827","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3695438","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T19:38:20Z","timestamp":1779478700000},"page":"10521-10534","source":"Crossref","is-referenced-by-count":0,"title":["FAM-HRI: Foundation-Model Assisted Multimodal Human\u2013Robot Interaction Combining Gaze and Speech"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9976-7422","authenticated-orcid":false,"given":"Yuzhi","family":"Lai","sequence":"first","affiliation":[{"name":"University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1887-6342","authenticated-orcid":false,"given":"Shenghai","family":"Yuan","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Nanyang Ave, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2140-4357","authenticated-orcid":false,"given":"Peizheng","family":"Li","sequence":"additional","affiliation":[{"name":"University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boya","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Kiefer","sequence":"additional","affiliation":[{"name":"University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianchen","family":"Deng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Nanyang Ave, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3299-2211","authenticated-orcid":false,"given":"Andreas","family":"Zell","sequence":"additional","affiliation":[{"name":"University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673243"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000224"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3502508"},{"key":"ref4","article-title":"Sticky-glance: Robust intent recognition for human robot collaboration via single-glance","author":"Lai","year":"2026","journal-title":"arXiv:2603.06121"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341944"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.126360"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759741"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10020054"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440844"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/s12984-021-00969-2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594045"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adj8124"},{"key":"ref14","article-title":"Project aria: A new tool for egocentric multi-modal AI research","author":"Engel","year":"2023","journal-title":"arXiv:2308.13561"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3580469"},{"key":"ref16","article-title":"What is the best 3D scene representation for robotics? From geometric to foundation models","author":"Deng","year":"2025","journal-title":"arXiv:2512.03422"},{"key":"ref17","first-page":"1","article-title":"PERAL: Perception-aware motion control for passive LiDAR excitation in spherical robots","volume-title":"Proc. IEEE Int. Conf. Robot. Autom. (ICRA)","author":"Yuan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2856264"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3530169"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3475208"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3127391"},{"key":"ref22","first-page":"3061","article-title":"Gesture-informed robot assistance via foundation models","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Lin"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25075-0_43"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00111"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342045"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3519904"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593580"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3594806.3594819"},{"key":"ref31","first-page":"361","article-title":"Alchemist: LLM-aided end-user development of robot applications","volume-title":"Proc. ACM\/IEEE Int. Conf. Human-Robot Interact.","author":"Karli"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3651029"},{"key":"ref33","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref35","first-page":"1","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ravi"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-5379-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1391745"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/304182.304187"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340976"},{"key":"ref42","first-page":"1","article-title":"Don\u2019t yell at your robot: Physical correction as the collaborative interface for language model powered robots","volume-title":"Proc. Robot. Sci. Syst. Workshop (RSSW)","author":"Zhang"},{"key":"ref43","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref45","article-title":"RPMS: Enhancing LLM-based embodied planning through rule-augmented memory synergy","author":"Yuan","year":"2026","journal-title":"arXiv:2603.17831"},{"key":"ref46","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889538"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02690"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11534298.pdf?arnumber=11534298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T19:50:35Z","timestamp":1781553035000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11534298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3695438","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}