{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:49:57Z","timestamp":1740102597941,"version":"3.37.3"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,4]]},"DOI":"10.1109\/robio58561.2023.10355013","type":"proceedings-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T19:20:45Z","timestamp":1703272845000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["A Modular Framework for Robot Embodied Instruction Following by Large Language Model"],"prefix":"10.1109","author":[{"given":"Long","family":"Li","sequence":"first","affiliation":[{"name":"Tongji University,The School of Electronics and Information,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tongji University,The School of Electronics and Information,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyu","family":"You","sequence":"additional","affiliation":[{"name":"Tongji University,The School of Electronics and Information,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language Guided Meta-Control for Embodied Instruction Following","author":"Goel","year":"2022","journal-title":"Computer Vision and Pattern Recognition"},{"key":"ref2","volume":"abs\/1712.05474","author":"Kolve","year":"2017","journal-title":"AI2-THOR: An Interactive 3D Environment for Visual AI"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref4","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"year":"2021","author":"Suglia","journal-title":"Embodied bert: A transformer model for embodied, language-guided visual task completion","key":"ref5"},{"key":"ref6","article-title":"FILM: following instructions in language with modular methods","volume":"abs\/2110.07342","author":"Min","year":"2021","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.18653\/v1\/2021.findings-acl.368"},{"volume-title":"Embodied AI Workshop CVPR","author":"Kim","article-title":"Agent with the big picture: Perceiving surroundings for interactive instruction following","key":"ref8"},{"year":"2022","author":"Liu","journal-title":"Lebp\u2013language expectation binding policy: A two-stream framework for embodied vision-and-language interaction task learning agents","key":"ref9"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/LRA.2022.3178804"},{"year":"2022","author":"Liu","journal-title":"A Planning based Neural-Symbolic Approach for Embodied Instruction Following","key":"ref11"},{"year":"2022","author":"Inoue","journal-title":"Prompter: Utilizing Large Language Model Prompting for a Data Efficient Embodied Instruction Following","key":"ref12"},{"key":"ref13","first-page":"877","article-title":"Roberta: A Robustly Optimized BERT Pretraining Approach","volume-title":"Proceedings of the 2020 IEEE\/CVF International Conference on Computer Vision Workshop","author":"Cheng"},{"volume-title":"International Conference on Learning Representations","author":"Hu","article-title":"LORA: LOW-RANK ADAPTATION OF LARGE LANGUAGE MODELS","key":"ref14"},{"year":"2021","author":"Radford","journal-title":"Language models are few-shot learners","key":"ref15"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1073\/pnas.93.4.1591"},{"year":"2020","author":"Singh","journal-title":"Moca: A modular object-centric approach for interactive instruction following","key":"ref17"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ICCV48922.2021.01564"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.24963\/ijcai.2021\/128"},{"key":"ref20","article-title":"A persistent spatial semantic representation for high-level natural language instruction execution","author":"Blukis","year":"2022","journal-title":"CORL"}],"event":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2023,12,4]]},"location":"Koh\u00a0Samui, Thailand","end":{"date-parts":[[2023,12,9]]}},"container-title":["2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10354348\/10354529\/10355013.pdf?arnumber=10355013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T20:17:23Z","timestamp":1705090643000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10355013\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/robio58561.2023.10355013","relation":{},"subject":[],"published":{"date-parts":[[2023,12,4]]}}}