{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:29:49Z","timestamp":1783974589168,"version":"3.55.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610784","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"4340-4348","source":"Crossref","is-referenced-by-count":26,"title":["How to Prompt Your Robot: A PromptBook for Manipulation Skills with Code as Policies"],"prefix":"10.1109","author":[{"given":"Montserrat Gonzalez","family":"Arenas","sequence":"first","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ted","family":"Xiao","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sumeet","family":"Singh","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vidhi","family":"Jain","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allen","family":"Ren","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quan","family":"Vuong","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jake","family":"Varley","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Herzog","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabel","family":"Leal","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean","family":"Kirmani","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mario","family":"Prats","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dorsa","family":"Sadigh","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vikas","family":"Sindhwani","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kanishka","family":"Rao","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacky","family":"Liang","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andy","family":"Zeng","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Ahn","year":"2022","journal-title":"Do as i can, not as i say: Grounding language in robotic affordances"},{"key":"ref2","author":"Huang","year":"2022","journal-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents"},{"key":"ref3","author":"Huang","year":"2023","journal-title":"Grounded decoding: Guiding text generation with grounded models for robot control"},{"key":"ref4","author":"Zeng","year":"2022","journal-title":"Socratic models: Composing zero-shot multimodal reasoning with language"},{"key":"ref5","author":"Wei","year":"2022","journal-title":"Chain of thought prompting elicits reasoning in large language models"},{"key":"ref6","author":"Kojima","year":"2022","journal-title":"Large language models are zero-shot reasoners"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"ref8","author":"Creswell","year":"2022","journal-title":"Selection-inference: Exploiting large language models for interpretable logical reasoning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref11","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"issue":"8","key":"ref12","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref13","author":"Chan","year":"2022","journal-title":"Transformers generalize differ ently from information stored in context vs in weights"},{"key":"ref14","author":"Silver","year":"2023","journal-title":"Generalized planning in pddl domains with pretrained large language models"},{"key":"ref15","author":"Yu","year":"2023","journal-title":"Language to rewards for robotic skill synthesis"},{"key":"ref16","first-page":"27 730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.022"},{"key":"ref18","article-title":"A neural network solves, explains, and generates university math problems by program synthesis and few-shot learning at human level","author":"Drori","year":"2021"},{"key":"ref19","volume-title":"Chain of thought prompting elicits reasoning in large language models","volume":"abs\/2201.11903","author":"Wei","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref21","article-title":"SLAP: Spatial-language attention policies","volume-title":"7th Annual Conference on Robot Learning","author":"Parashar"},{"key":"ref22","author":"Kwon","year":"2023","journal-title":"Reward design with language models"},{"key":"ref23","article-title":"Language instructed reinforcement learning for human-ai coordination","volume-title":"40th International Conference on Machine Learning (ICML)","author":"Hu"},{"key":"ref24","article-title":"Gesture-informed robot assistance via foundation models","volume-title":"7th Annual Conference on Robot Learning","author":"Lin"},{"key":"ref25","article-title":"Transformers are adaptable task planners","volume-title":"6th Annual Conference on Robot Learning","author":"Jain"},{"key":"ref26","article-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref27","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"abs\/1910.10683","author":"Raffel","year":"2019"},{"key":"ref28","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021"},{"key":"ref29","volume-title":"Lima: Less is more for alignment","volume":"abs\/2305.11206","author":"Zhou","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7979"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2010.5453186"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-00065-7_28","article-title":"Learning to parse natural language commands to a robot control system","volume-title":"International Symposium on Experimental Robotics (ISER)","author":"Matuszek"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00209"},{"key":"ref34","author":"Hermann","year":"2017","journal-title":"Grounded language learning in a simulated 3d world"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11832"},{"key":"ref36","author":"Hill","year":"2020","journal-title":"Human instruction-following with deep reinforcement learning via transfer-learning from text"},{"key":"ref37","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","author":"Jang","year":"2022","journal-title":"CoRL"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.047"},{"key":"ref39","article-title":"Homerobot: Open-vocabulary mobile manipulation","volume-title":"7th Annual Conference on Robot Learning","author":"Yenamandra"},{"key":"ref40","volume-title":"Rt-1: Robotics transformer for real-world control at scale","volume":"abs\/2212.06817","author":"Brohan","year":"2022"},{"key":"ref41","article-title":"Emergent abilities of large language models","volume-title":"Trans. Mach. Learn. Res.","volume":"2022","author":"Wei","year":"2022"},{"key":"ref42","volume-title":"Language models are few-shot learners","volume":"abs\/2005.14165","author":"Brown","year":"2020"},{"key":"ref43","article-title":"Large language models as general pattern machines","volume-title":"Proceedings of the 7th Conference on Robot Learning (CoRL)","author":"Mirchandani"},{"key":"ref44","first-page":"20","article-title":"Chat-gpt for robotics: Design principles and model abilities","volume":"2","author":"Vemprala","year":"2023","journal-title":"Microsoft Auton. Syst. Robot. Res"},{"key":"ref45","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023"},{"key":"ref46","author":"Yang","year":"2023","journal-title":"Large language models as optimizers"},{"key":"ref47","volume-title":"Integrating action knowledge and llms for task planning and situation handling in open worlds","volume":"abs\/2305.17590","author":"Ding","year":"2023"},{"key":"ref48","author":"Zhang","year":"2022","journal-title":"Automatic chain of thought prompting in large language models"},{"key":"ref49","author":"Gandhi","year":"2023","journal-title":"Strategic reasoning with language models"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref51","author":"Varley","year":"2023","journal-title":"Embodied ai with two arms:zero-shot learning, safety and modularity"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610784.pdf?arnumber=10610784","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:55:42Z","timestamp":1723269342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610784\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610784","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}