{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T20:29:46Z","timestamp":1785356986494,"version":"3.55.0"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N000142212121"],"award-info":[{"award-number":["N000142212121"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127987","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"5961-5968","source":"Crossref","is-referenced-by-count":10,"title":["Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding"],"prefix":"10.1109","author":[{"given":"Joshua","family":"Jones","sequence":"first","affiliation":[{"name":"Berkeley AI Research (BAIR),UC Berkeley,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oier","family":"Mees","sequence":"additional","affiliation":[{"name":"Berkeley AI Research (BAIR),UC Berkeley,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carmelo","family":"Sferrazza","sequence":"additional","affiliation":[{"name":"Berkeley AI Research (BAIR),UC Berkeley,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyle","family":"Stachowicz","sequence":"additional","affiliation":[{"name":"Berkeley AI Research (BAIR),UC Berkeley,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[{"name":"Berkeley AI Research (BAIR),UC Berkeley,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[{"name":"Berkeley AI Research (BAIR),UC Berkeley,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2621"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852779"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"ref5","article-title":"Open-vla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref7","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Scaling cross-embodied learning: One policy for manipulation, navigation, locomotion and aviation","volume-title":"Conference on Robot Learning","author":"Doshi","year":"2024"},{"key":"ref9","article-title":"Open X-Embodiment: Robotic learning datasets and RT-X models","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Collaboration"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref11","article-title":"Bridgedata v2: A dataset for robot learning at scale","volume-title":"Conference on Robot Learning (CoRL)","author":"Walke"},{"key":"ref12","article-title":"Latent plans for task agnostic offline reinforcement learning","volume-title":"Proceedings of the 6th Conference on Robot Learning (CoRL)","author":"Rosete-Beas"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"ref14","article-title":"A touch, vision, and language dataset for multimodal alignment","volume-title":"Forty-first International Conference on Machine Learning","author":"Fu"},{"key":"ref15","article-title":"Maniwav: Learning robot manipulation from in-the-wild audio-visual data","volume-title":"8th Annual Conference on Robot Learning","author":"Liu"},{"key":"ref16","article-title":"Towards comprehensive multimodal perception: Introducing the touch-language-vision dataset","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref19","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160969"},{"key":"ref22","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Bridging language and action: A survey of language-based robot manipulation","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02488"},{"key":"ref25","first-page":"314","article-title":"The feeling of success: Does touch sensing help predict grasp outcomes?","volume-title":"Conference on Robot Learning","author":"Calandra"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3084880"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341006"},{"key":"ref28","article-title":"Paligemma: A versatile 3b vlm for transfer","author":"Beyer","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Robot utility models: General policies for zero-shot deployment in new environments","author":"Etukuru","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Robonet: Large-scale multi-robot learning","author":"Dasari","year":"2019","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Robotic control via embodied chain-of-thought reasoning","volume-title":"Conference on Robot Learning","author":"Zawalski","year":"2024"},{"key":"ref32","first-page":"2549","article-title":"General in-hand object rotation with vision and touch","volume-title":"Conference on Robot Learning","author":"Qi"},{"key":"ref33","article-title":"The power of the senses: Generalizable manipulation from vision and touch through masked multimodal learning","author":"Sferrazza","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759048"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611305"},{"key":"ref36","article-title":"See, hear, and feel: Smart sensory fusion for robotic manipulation","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610532"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01086"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2959445"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611407"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref42","article-title":"Learning visuotactile skills with two multifingered hands","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","first-page":"129","article-title":"Integration of vision, force and tactile sensing for grasping","volume":"4","author":"Miller","year":"1999","journal-title":"Int. J. Intell. Mach"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.066"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533654"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"4","key":"ref50","article-title":"Chatgpt: Optimizing language models for dialogue","volume":"2","author":"Schulman","year":"2022","journal-title":"OpenAI blog"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref52","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"key":"ref53","article-title":"PaliVLA","volume-title":"GitHub repository","author":"Stachowicz","year":"2024"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127987.pdf?arnumber=11127987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:15:17Z","timestamp":1756880117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127987","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}