{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:18:25Z","timestamp":1762237105999,"version":"build-2065373602"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,25]]},"DOI":"10.1109\/ro-man63969.2025.11217852","type":"proceedings-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:42:29Z","timestamp":1762195349000},"page":"1609-1616","source":"Crossref","is-referenced-by-count":0,"title":["Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers"],"prefix":"10.1109","author":[{"given":"Takumi","family":"Kobayashi","sequence":"first","affiliation":[{"name":"The University of Osaka,Graduate School of Information Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masato","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"The University of Osaka,Graduate School of Information Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thanpimon","family":"Buamanee","sequence":"additional","affiliation":[{"name":"The University of Osaka,Graduate School of Information Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Uranishi","sequence":"additional","affiliation":[{"name":"The University of Osaka,Graduate School of Information Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3153728"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSMC.2023.3238855"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981917"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3395626"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802498"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN60168.2024.10731313"},{"key":"ref7","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on robot learning","author":"Brohan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802322"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3541200"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594489"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3155255"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/OJIES.2022.3149333"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/AIM55361.2024.10637173"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"article-title":"Dabi: Evaluation of data augmentation methods using downsampling in bilateral control-based imitation learning with images","year":"2024","author":"Kobayashi","key":"ref15"},{"key":"ref16","first-page":"13 139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume":"33","author":"Stepputtis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3466076"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610090"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICARM62033.2024.10715821"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/3516.491410"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/41.222648"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"article-title":"Distilbert, a distillfed version of bert: smaller, faster, cheaper and lighter","year":"2019","author":"Sanh","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.127"}],"event":{"name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2025,8,25]]},"location":"Eindhoven, Netherlands","end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11217544\/11217526\/11217852.pdf?arnumber=11217852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:14:29Z","timestamp":1762236869000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11217852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ro-man63969.2025.11217852","relation":{},"subject":[],"published":{"date-parts":[[2025,8,25]]}}}