{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T01:53:19Z","timestamp":1785376399547,"version":"3.55.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3310935","type":"journal-article","created":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T17:39:52Z","timestamp":1693503592000},"page":"95060-95078","source":"Crossref","is-referenced-by-count":80,"title":["ChatGPT Empowered Long-Step Robot Control in Various Environments: A Case Application"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8278-2373","authenticated-orcid":false,"given":"Naoki","family":"Wake","sequence":"first","affiliation":[{"name":"Applied Robotics Research, Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsushi","family":"Kanehira","sequence":"additional","affiliation":[{"name":"Applied Robotics Research, Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5408-3089","authenticated-orcid":false,"given":"Kazuhiro","family":"Sasabuchi","sequence":"additional","affiliation":[{"name":"Applied Robotics Research, Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7457-2878","authenticated-orcid":false,"given":"Jun","family":"Takamatsu","sequence":"additional","affiliation":[{"name":"Applied Robotics Research, Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9758-9357","authenticated-orcid":false,"given":"Katsushi","family":"Ikeuchi","sequence":"additional","affiliation":[{"name":"Applied Robotics Research, Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160640"},{"key":"ref57","year":"2023","journal-title":"GPT-4"},{"key":"ref12","first-page":"7973","article-title":"Learning neuro-symbolic programs for language guided robot manipulation","author":"singh","year":"2023","journal-title":"Proc IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref56","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"ouyang","year":"2022","journal-title":"2022 Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref15","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"zeng","year":"2022","journal-title":"arXiv 2204 00598"},{"key":"ref14","article-title":"Robot task planning and situation handling in open worlds","author":"ding","year":"2022","journal-title":"arXiv 2210 01287"},{"key":"ref58","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"touvron","year":"2023","journal-title":"arXiv 2307 09288"},{"key":"ref53","article-title":"Does ChatGPT resemble humans in language use?","author":"cai","year":"2023","journal-title":"arXiv 2303 08014"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3282111"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref55","article-title":"Training compute-optimal large language models","author":"hoffmann","year":"2022","journal-title":"arXiv 2203 15556"},{"key":"ref10","article-title":"Task and motion planning with large language models for object rearrangement","author":"ding","year":"2023","journal-title":"arXiv 2303 06247"},{"key":"ref54","year":"2023","journal-title":"Azure OpenAI—Data Privacy"},{"key":"ref17","article-title":"Planning with large language models via corrective re-prompting","author":"raman","year":"2022","journal-title":"arXiv 2211 09935"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1134\/S1064562422060138"},{"key":"ref18","article-title":"Translating natural language to planning goals with large-language models","author":"xie","year":"2023","journal-title":"arXiv 2302 05128"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-101119-071628"},{"key":"ref50","article-title":"Task-sequencing simulator: Integrated machine learning to execution simulation for robot manipulation","author":"sasabuchi","year":"2023","journal-title":"arXiv 2301 01382"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1002\/tee.23523"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1002\/tee.23008"},{"key":"ref48","article-title":"Learning-from-observation system considering hardware-level reusability","author":"takamatsu","year":"2022","journal-title":"arXiv 2212 09242"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/AIM46323.2023.10196126"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562102"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3434074.3447152"},{"key":"ref44","article-title":"Applying learning-from-observation to household service robots: Three common-sense formulations","author":"ikeuchi","year":"2023","journal-title":"arXiv 2304 09966"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3044029"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000167"},{"key":"ref8","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","author":"brohan","year":"2023","journal-title":"Proc Conf Robot Learn"},{"key":"ref7","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","author":"shridhar","year":"2023","journal-title":"Proc Conf Robot Learn"},{"key":"ref9","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"huang","year":"2022","journal-title":"arXiv 2207 05608"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636342"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341289"},{"key":"ref6","article-title":"VIMA: General robot manipulation with multimodal prompts","author":"jiang","year":"2022","journal-title":"arXiv 2210 03094"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SII52469.2022.9708836"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-023-01408-z"},{"key":"ref35","article-title":"Evaluating large language models trained on code","author":"chen","year":"2021","journal-title":"arXiv 2107 03374"},{"key":"ref34","article-title":"Related systems","author":"kuhn","year":"1956","journal-title":"Annals of Mathematics Studies"},{"key":"ref37","article-title":"Generating executable action plans with environmentally-aware language models","author":"gramopadhye","year":"2022","journal-title":"arXiv 2210 04964"},{"key":"ref36","first-page":"104","article-title":"Minsky’s frame system theory","author":"minsky","year":"1975","journal-title":"Proc Workshop Theor Issues Natural Lang Process"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref30","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":"ref33","article-title":"Semantic constraints to represent common sense required in household actions for multi-modal learning-from-observation robot","author":"ikeuchi","year":"2021","journal-title":"arXiv 2103 02201"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF49454.2021.9382750"},{"key":"ref2","year":"2023","journal-title":"ChatGPT"},{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Proc Adv Neur Inf Process Sys"},{"key":"ref39","first-page":"1","article-title":"Grasp-type recognition leveraging object affordance","author":"wake","year":"2020","journal-title":"Proc HOBI-RO-MAN Workshop"},{"key":"ref38","year":"2023","journal-title":"Microsoft Azure"},{"key":"ref24","article-title":"Language conditioned imitation learning over unstructured data","author":"lynch","year":"2020","journal-title":"arXiv 2005 07648"},{"key":"ref23","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","author":"huang","year":"2022","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","article-title":"Text2Motion: From natural language instructions to feasible plans","author":"lin","year":"2023","journal-title":"arXiv 2303 12153"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161125"},{"key":"ref20","article-title":"Natural language robot programming: NLP integrated with autonomous robotic grasping","author":"khan","year":"2023","journal-title":"arXiv 2304 02993"},{"key":"ref22","article-title":"Errors are useful prompts: Instruction guided task programming with verifier-assisted iterative prompting","author":"skreta","year":"2023","journal-title":"arXiv 2303 14100"},{"key":"ref21","article-title":"Remote task-oriented grasp area teaching by non-experts through interactive segmentation and few-shot learning","author":"kaynar","year":"2023","journal-title":"arXiv 2303 10195"},{"key":"ref28","article-title":"Instruction-following agents with multimodal transformer","author":"liu","year":"2022","journal-title":"arXiv 2210 13431"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3265893"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10235949.pdf?arnumber=10235949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T18:04:53Z","timestamp":1696269893000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10235949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3310935","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}