{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:12Z","timestamp":1766061612251,"version":"3.48.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11245926","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"8096-8102","source":"Crossref","is-referenced-by-count":1,"title":["Look Before You Leap: Using Serialized State Machine for Language Conditioned Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Tong","family":"Mu","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Department of Computer Science,Baltimore,MD,USA,21218"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihao","family":"Liu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Computer Science,Baltimore,MD,USA,21218"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehran","family":"Armand","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Computer Science,Baltimore,MD,USA,21218"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","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"},{"article-title":"Evaluating large language models trained on code","year":"2021","author":"Chen","key":"ref2"},{"article-title":"Gensim: Generating robotic simulation tasks via large language models","year":"2023","author":"Wang","key":"ref3"},{"article-title":"Gensim2: Scaling robot data generation with multi-modal and reasoning llms","year":"2024","author":"Hua","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"article-title":"More than eleven thousand words: Towards using language models for robotic sorting of unseen objects into arbitrary categories","volume-title":"Workshop on language and robotics at CoRL 2022","author":"H\u00f8eg","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref8","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on robot learning","author":"Shridhar"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247229"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(71)90010-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6739"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1800514"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2008.11.011"},{"issue":"3","key":"ref14","first-page":"57","article-title":"Ff: The fast-forward planning system","volume":"22","author":"Hoffmann","year":"2001","journal-title":"AI magazine"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1705"},{"article-title":"Do as i can, not as i say: Grounding language in robotic affordances","year":"2022","author":"Ahn","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.395"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802322"},{"article-title":"A roadmap towards automated and regulated robotic systems","year":"2024","author":"Liu","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980391"},{"article-title":"Inner monologue: Embodied reasoning through planning with language models","year":"2022","author":"Huang","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834116"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2004.03.002"},{"key":"ref28","article-title":"One-shot imitation learning","volume":"30","author":"Duan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref29","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","volume-title":"Conference on robot learning","author":"Finn"},{"key":"ref30","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref31"},{"article-title":"Octo: An open-source generalist robot policy","year":"2024","author":"Team","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.181"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709321"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11245926.pdf?arnumber=11245926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:35:33Z","timestamp":1766061333000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11245926","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}