{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T18:35:54Z","timestamp":1772303754234,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981810","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"978-984","source":"Crossref","is-referenced-by-count":39,"title":["Reshaping Robot Trajectories Using Natural Language Commands: A Study of Multi-Modal Data Alignment Using Transformers"],"prefix":"10.1109","author":[{"given":"Arthur","family":"Bucker","sequence":"first","affiliation":[{"name":"Technische Universität München"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis","family":"Figueredo","sequence":"additional","affiliation":[{"name":"Technische Universität München"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sami","family":"Haddadinl","sequence":"additional","affiliation":[{"name":"Technische Universität München"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashish","family":"Kapoor","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Ma","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rogerio","family":"Bonatti","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model","author":"Smith","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref6","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref7","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume":"33","author":"Alwassel","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982241"},{"key":"ref9","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar","year":"2022"},{"key":"ref11","article-title":"A recurrent vision-and-language bert for navigation. arxiv 2021","author":"Hong","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211046285"},{"key":"ref13","article-title":"Semantically grounded object matching for robust robotic scene rearrangement","author":"Goodwin","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.012"},{"key":"ref15","article-title":"From language to goals: Inverse reinforcement learning for vision-based instruction following","author":"Fu","year":"2019","journal-title":"arXiv preprint"},{"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","article-title":"Zero-shot task adaptation using natural language","author":"Goyal","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920917755"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.55417\/fr.2022040"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90002-2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-101119-071628"},{"issue":"6","key":"ref23","first-page":"4","article-title":"Walk the talk: Connecting language, knowledge, and action in route instructions","volume":"2","author":"MacMahon","year":"2006","journal-title":"Def"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907843"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.047"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2013.IX.023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref29","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref31","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume":"34","author":"Szot","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref35","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1063"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref38","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412190"},{"key":"ref40","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref41","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560745"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152817"},{"key":"ref45","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Large batch optimization for deep learning: Training bert in 76 minutes","author":"You","year":"2019","journal-title":"arXiv preprint"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Kyoto, Japan","start":{"date-parts":[[2022,10,23]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981810.pdf?arnumber=9981810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:41:24Z","timestamp":1706758884000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981810\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981810","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}