{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:19:48Z","timestamp":1759331988260,"version":"3.32.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802198","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"9644-9651","source":"Crossref","is-referenced-by-count":2,"title":["MuTT: A Multimodal Trajectory Transformer for Robot Skills"],"prefix":"10.1109","author":[{"given":"Claudius","family":"Kienle","sequence":"first","affiliation":[{"name":"ArtiMinds Robotics,Karlsruhe,Germany"}]},{"given":"Benjamin","family":"Alt","sequence":"additional","affiliation":[{"name":"ArtiMinds Robotics,Karlsruhe,Germany"}]},{"given":"Onur","family":"Celik","sequence":"additional","affiliation":[{"name":"KIT,Autonomous Learning Robots,Germany"}]},{"given":"Philipp","family":"Becker","sequence":"additional","affiliation":[{"name":"KIT,Autonomous Learning Robots,Germany"}]},{"given":"Darko","family":"Katic","sequence":"additional","affiliation":[{"name":"ArtiMinds Robotics,Karlsruhe,Germany"}]},{"given":"Rainer","family":"J\u00e4kel","sequence":"additional","affiliation":[{"name":"ArtiMinds Robotics,Karlsruhe,Germany"}]},{"given":"Gerhard","family":"Neumann","sequence":"additional","affiliation":[{"name":"KIT,Autonomous Learning Robots,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793542"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2009.4913000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630615"},{"key":"ref4","first-page":"282","article-title":"Robot skills for manufacturing: From concept to industrial deployment","volume-title":"Robotics and Computer-Integrated Manufacturing","volume":"37","author":"Pedersen","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"issue":"4","key":"ref6","first-page":"2325","article-title":"ProDMP: A Unified Perspective on Dynamic and Probabilistic Movement Primitives","volume-title":"IEEE Robotics and Automation Letters","volume":"8","author":"Li","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/4-431-31381-8_23"},{"issue":"4","key":"ref8","first-page":"581","article-title":"Specification of force-controlled actions in the \u201dtask frame formalism\"-a synthesis","volume-title":"IEEE Transactions on Robotics and Automation","volume":"12","author":"Bruyninckx","year":"1996"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561206"},{"article-title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","year":"2023","author":"Gu","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506796"},{"article-title":"Masked Vision-Language Transformers for Scene Text Recognition","year":"2022","author":"Wu","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"ref15","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.acl-long.393","article-title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","author":"Ao","year":"2022"},{"article-title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","year":"2022","author":"Shi","key":"ref17"},{"article-title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","year":"2019","author":"Li","key":"ref18"},{"article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","year":"2024","author":"Reid","key":"ref19"},{"article-title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","year":"2023","author":"Brohan","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"article-title":"PaLM-E: An Embodied Multimodal Language Model","year":"2023","author":"Driess","key":"ref22"},{"key":"ref23","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2023.XIX.025","article-title":"RT-1: Robotics Transformer for Real-World Control at Scale","author":"Brohan","year":"2023"},{"key":"ref26","first-page":"8282","article-title":"Real2Sim2Real: Self-Supervised Learning of Physical Single-Step Dynamic Actions for Planar Robot Casting","volume-title":"2022 International Conference on Robotics and Automation (ICRA)","author":"Lim"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161574"},{"key":"ref28","first-page":"9156","article-title":"Learning Universal Policies via Text-Guided Video Generation","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Du","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-022-01688-z"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3064065"},{"key":"ref31","first-page":"8887","article-title":"Heuristic-free Optimization of Force-Controlled Robot Search Strategies in Stochastic Environments","volume-title":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Alt"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1995.488968"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/evco.1993.1.1.1"},{"volume-title":"Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Robotics","year":"2020","author":"Berkenkamp","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-015-9463-9"},{"key":"ref37","article-title":"Attention is All you Need","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref38","first-page":"978","article-title":"Multimodal pretraining unmasked: A meta-analysis and a unified framework of vision-and-language BERTs","volume-title":"Transactions of the Association for Computational Linguistics","volume":"9","author":"Bugliarello","year":"2021"},{"volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","year":"2021","author":"Dosovitskiy","key":"ref39"},{"article-title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","year":"2021","author":"Janner","key":"ref40"},{"key":"ref41","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"International conference on machine learning","author":"Gehring"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2023.XIX.032","volume-title":"Language-Driven Representation Learning for Robotics","author":"Karamcheti","year":"2023"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1007\/978-3-540-87536-9_42","article-title":"Episodic Reinforcement Learning by Logistic Reward-Weighted Regression","volume-title":"Artificial Neural Networks - ICANN 2008","volume":"5163","author":"Wierstra","year":"2008"},{"volume-title":"Offline Reinforcement Learning with Implicit Q-Learning","year":"2021","author":"Kostrikov","key":"ref44"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802198.pdf?arnumber=10802198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:00:14Z","timestamp":1735196414000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802198\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802198","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}