{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:20:35Z","timestamp":1791912035537,"version":"4.3.4"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,8]]},"DOI":"10.1109\/icarm62033.2024.10715872","type":"proceedings-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T17:27:32Z","timestamp":1729272452000},"page":"978-983","source":"Crossref","is-referenced-by-count":22,"title":["Embodied AI with Large Language Models: A Survey and New HRI Framework"],"prefix":"10.1109","author":[{"given":"Ming-Yi","family":"Lin","sequence":"first","affiliation":[{"name":"Yuan Ze University,Department of Computer Science and Engineering,Taoyuan,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ou-Wen","family":"Lee","sequence":"additional","affiliation":[{"name":"Yuan Ze University,Department of Computer Science and Engineering,Taoyuan,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chih-Ying","family":"Lu","sequence":"additional","affiliation":[{"name":"Yuan Ze University,Department of Computer Science and Engineering,Taoyuan,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/daed_a_01902"},{"key":"ref2","first-page":"20","article-title":"Chatgpt for robotics: Design principles and model abilities","volume":"2","author":"Vemprala","year":"2023","journal-title":"Microsoft Auton. Syst. Robot. Res"},{"key":"ref3","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref4","article-title":"VIMA: General Robot Manipulation with Multimodal Prompts","author":"Jiang","year":"2022","journal-title":"arXiv:2210.03094"},{"key":"ref5","article-title":"PaLM-E: An Embodied Multimodal Language Model","author":"Driess","year":"2023","journal-title":"arXiv:2303.03378"},{"key":"ref6","article-title":"RT-1: Robotics Transformer for Real-World Control at Scale","author":"Brohan","year":"2022","journal-title":"arXiv:2212.06817"},{"key":"ref7","article-title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","author":"Brohan","year":"2023","journal-title":"arXiv:2307.15818"},{"key":"ref8","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/machines10100913"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105694"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/machines11010048"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.7771\/2157-9288.1223"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/10494820.2021.2023890"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1115\/1.4047855"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3034808"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s43154-020-00006-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogr.2023.04.001"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.12.112"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3424153"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.annals.2020.103036"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-020-01641-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1108\/JOSM-05-2020-0148"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1093\/geroni\/igab013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2200563"},{"issue":"28","key":"ref25","first-page":"1501","article-title":"Adoption of robots and service automation by tourism and hospitality companies","volume":"27","author":"Ivanov","year":"2017","journal-title":"Revista Turismo & Desenvolvimento"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-013-0220-0"},{"key":"ref27","volume-title":"Boston Dynamics, Making Chat (ro)Bots","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.532375"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adh0972"},{"key":"ref33","article-title":"Once is enough: Helping robots learn quickly in new environments","author":"Hardesty","year":"2023","journal-title":"USC Viterbi"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00752-z"},{"key":"ref35","article-title":"Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation","author":"Dai","year":"2023","journal-title":"arXiv:2310.07968"},{"key":"ref36","article-title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","author":"Huang","year":"2023","journal-title":"arXiv:2307.05973"},{"key":"ref37","article-title":"Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review","author":"Su","year":"2024","journal-title":"arXiv:2402.10350"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.semeval-1.72"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3158231"},{"key":"ref40","first-page":"71","article-title":"Didm3d: Decoupling instance depth for monocular 3d object detection","volume-title":"European Conference on Computer Vision","author":"Peng"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013848"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123375"},{"key":"ref43","article-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 International Conference on Advanced Robotics and Mechatronics (ICARM)","location":"Tokyo, Japan","start":{"date-parts":[[2024,7,8]]},"end":{"date-parts":[[2024,7,10]]}},"container-title":["2024 International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10715684\/10715739\/10715872.pdf?arnumber=10715872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T04:53:46Z","timestamp":1729313626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10715872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,8]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icarm62033.2024.10715872","relation":{},"subject":[],"published":{"date-parts":[[2024,7,8]]}}}