{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T04:21:24Z","timestamp":1769919684761,"version":"3.49.0"},"reference-count":55,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127404","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"16517-16524","source":"Crossref","is-referenced-by-count":1,"title":["STEER: Flexible Robotic Manipulation via Dense Language Grounding"],"prefix":"10.1109","author":[{"given":"Laura","family":"Smith","sequence":"first","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Irpan","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Montserrat Gonzalez","family":"Arenas","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sean","family":"Kirmani","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dmitry","family":"Kalashnikov","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhruv","family":"Shah","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ted","family":"Xiao","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref3","article-title":"BC-z: Zero-shot task generalization with robotic imitation learning","volume-title":"5th Annual Conference on Robot Learning","author":"Jang","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref5","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"ref8","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Scaling cross-embodied learning: One policy for manipulation, navigation, locomotion and aviation","author":"Doshi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","volume-title":"New York:Farrar, Straus and Giroux","author":"Kahneman","year":"2011"},{"key":"ref11","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"6th Annual Conference on Robot Learning","author":"Ahn","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.096"},{"key":"ref14","volume-title":"Behavior generation with latent actions","author":"Lee","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref16","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref17","volume-title":"Gpt-4 technical report","year":"2024"},{"key":"ref18","volume-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2024"},{"key":"ref19","author":"Stone","year":"2023","journal-title":"Open-world object manipulation using pre-trained visionlanguage models"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.029"},{"key":"ref21","volume-title":"Policy adaptation via language optimization: Decomposing tasks for few-shot imitation","author":"Myers","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610606"},{"key":"ref23","article-title":"Relay policy learning: Solving long horizon tasks via imitation and reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Gupta","year":"2019"},{"key":"ref24","article-title":"Zero-shot robotic manipulation with pretrained imageediting diffusion models","volume-title":"ArXiv","author":"Black","year":"2023"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"4076","DOI":"10.1109\/IROS47612.2022.9981999","article-title":"Planning to practice: Efficient online fine-tuning by composing goals in latent space","volume-title":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Fang","year":"2022"},{"key":"ref26","article-title":"Rt-trajectory: Robotic task generalization via hindsight trajectory sketches","author":"Gu","year":"2024","journal-title":"Robotics: Science and Systems (RSS)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.092"},{"key":"ref28","article-title":"Vima: General robot manipulation with multimodal prompts","volume-title":"Fortieth International Conference on Machine Learning","author":"Jiang","year":"2023"},{"key":"ref29","article-title":"Pivot: Iterative visual prompting elicits actionable knowledge for vlms","volume-title":"Forty-first International Conference on Machine Learning","author":"Nasiriany","year":"2024"},{"key":"ref30","article-title":"Composing complex skills by learning transition policies","volume-title":"International Conference on Learning Representations","author":"Lee","year":"2019"},{"key":"ref31","article-title":"Learning to coordinate manipulation skills via skill behavior diversification","volume-title":"International conference on learning representations","author":"Lee","year":"2019"},{"key":"ref32","first-page":"4654","article-title":"Taco: Learning task decomposition via temporal alignment for control","volume-title":"International Conference on Machine Learning. PMLR","author":"Shiarlis","year":"2018"},{"key":"ref33","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","author":"Gupta","year":"2019","journal-title":"CoRL"},{"key":"ref34","article-title":"Discovering motor programs by recomposing demonstrations","volume-title":"International Conference on Learning Representations","author":"Shankar","year":"2019"},{"key":"ref35","article-title":"Accelerating reinforcement learning with learned skill priors","volume-title":"Conference on Robot Learning (CoRL)","author":"Pertsch","year":"2020"},{"key":"ref36","article-title":"Parrot: Data-driven behavioral priors for reinforcement learning","author":"Singh","year":"2021","journal-title":"ICLR"},{"key":"ref37","article-title":"Learning to compose hierarchical object-centric controllers for robotic manipulation","author":"Sharma","year":"2020","journal-title":"arXiv preprint"},{"key":"ref38","first-page":"21847","article-title":"Accelerating robotic reinforcement learning via parameterized action primitives","volume":"34","author":"Dalal","year":"2021","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref40","article-title":"Extract: Efficient policy learning by extracting transferrable robot skills from offline data","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref42","article-title":"Data-efficient hierarchical reinforcement learning","volume":"31","author":"Nachum","year":"2018","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref43","article-title":"Mcp: Learning composable hierarchical control with multiplicative compositional policies","volume":"32","author":"Peng","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00878"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00328"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.012"},{"key":"ref48","article-title":"Data quality in imitation learning","volume":"36","author":"Belkhale","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","doi-asserted-by":"crossref","DOI":"10.1109\/ITSC.2017.8317738","volume-title":"Simultaneous policy learning and latent state inference for imitating driver behavior","author":"Morton","year":"2017"},{"key":"ref50","first-page":"1547","article-title":"Droid: Learning from offline heterogeneous demonstrations via reward-policy distillation","volume-title":"Proceedings of The 7th Conference on Robot Learning, ser. Proceedings of Machine Learning Research","volume":"229","author":"Jayanthi","year":"2023"},{"key":"ref51","volume-title":"Multi-modal imitation learning from unstructured demonstrations using generative adversarial nets","author":"Hausman","year":"2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610784"},{"key":"ref53","volume-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.049"}],"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\/11127404.pdf?arnumber=11127404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:15:21Z","timestamp":1756880121000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127404","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}