{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T22:19:02Z","timestamp":1777328342229,"version":"3.51.4"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI Grants-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["JP23K16975"],"award-info":[{"award-number":["JP23K16975"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI Grants-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["JP25K15292"],"award-info":[{"award-number":["JP25K15292"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Japan Science and Technology Agency (JST) Moonshot Research and Development Program","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}]},{"name":"JST Support for Pioneering Research Initiated by the Next Generation","award":["JPMJSP2101"],"award-info":[{"award-number":["JPMJSP2101"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3647727","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T18:31:48Z","timestamp":1766514708000},"page":"216937-216955","source":"Crossref","is-referenced-by-count":1,"title":["Spatial Concepts-Based Prompts With Large Language Models for Robot Action Planning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9080-902X","authenticated-orcid":false,"given":"Shoichi","family":"Hasegawa","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Engineering, Ritsumeikan University, Ibaraki, Osaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshinobu","family":"Hagiwara","sequence":"additional","affiliation":[{"name":"Faculty of Science and Engineering, Soka University, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0678-1103","authenticated-orcid":false,"given":"Akira","family":"Taniguchi","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University, Ibaraki, Osaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9795-6153","authenticated-orcid":false,"given":"Lotfi","family":"El Hafi","sequence":"additional","affiliation":[{"name":"Research Organization of Science and Technology, Ritsumeikan University, Kusatsu, Shiga, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5682-2076","authenticated-orcid":false,"given":"Tadahiro","family":"Taniguchi","sequence":"additional","affiliation":[{"name":"Research Organization of Science and Technology, Ritsumeikan University, Kusatsu, Shiga, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.47613\/reflektif.2024.176"},{"key":"ref2","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv:2204.01691"},{"key":"ref3","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\/icra48891.2023.10160591"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161534"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160969"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3387941"},{"key":"ref9","article-title":"Vision and language navigation in the real world via online visual language mapping","author":"Xu","year":"2023","journal-title":"arXiv:2310.10822"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63596-0_10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611640"},{"key":"ref12","article-title":"PaLM-E: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv:2303.03378"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1561\/2300000059"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2017.8202243"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-020-09905-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2019.1694068"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2021.1890212"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/sii55687.2023.10039318"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/18824889.2023.2283954"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2023.2225175"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/smc53992.2023.10394143"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2018.8594481"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn60899.2024.10651337"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iros45743.2020.9340989"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2019.2934509"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3444478"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2016.1164622"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2018.2867772"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610599"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128343"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00387"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00943"},{"key":"ref33","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"Kolve","year":"2017","journal-title":"arXiv:1712.05474"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342165"},{"key":"ref35","article-title":"ObjectNav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020","journal-title":"arXiv:2006.13171"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9812027"},{"key":"ref37","article-title":"ZSON: Zero-shot object-goal navigation using multimodal goal embeddings","author":"Majumdar","year":"2022","journal-title":"arXiv:2206.12403"},{"key":"ref38","article-title":"HomeRobot: Open-vocabulary mobile manipulation","author":"Yenamandra","year":"2023","journal-title":"arXiv:2306.11565"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2723009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.878"},{"key":"ref41","article-title":"Large language models are zero-shot reasoners","author":"Kojima","year":"2022","journal-title":"arXiv:2205.11916"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlp4convai-1.5"},{"key":"ref43","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref44","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"arXiv:2201.11903"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2016.7487442"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/mra.2015.2448951"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9811809"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1186\/s40648-019-0132-3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2022.2068353"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ssrr.2011.6106777"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161317"},{"key":"ref53","article-title":"Tree-Planner: Efficient close-loop task planning with large language models","author":"Hu","year":"2023","journal-title":"arXiv:2310.08582"},{"key":"ref54","article-title":"A survey on LLM-as-a-Judge","author":"Gu","year":"2024","journal-title":"arXiv:2411.15594"},{"key":"ref55","article-title":"Robots that ask for help: Uncertainty alignment for large language model planners","author":"Ren","year":"2023","journal-title":"arXiv:2307.01928"},{"key":"ref56","article-title":"REFLECT: Summarizing robot experiences for failure explanation and correction","author":"Liu","year":"2023","journal-title":"arXiv:2306.15724"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ro-man63969.2025.11217563"},{"key":"ref58","article-title":"Toward ownership understanding of objects: Active question generation with large language model and probabilistic generative model","author":"Hashimoto","year":"2025","journal-title":"arXiv:2509.12754"},{"key":"ref59","article-title":"Multi-robot task planning for multi-object retrieval tasks with distributed on-site knowledge via large language models","author":"Murata","year":"2025","journal-title":"arXiv:2509.12838"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127619"},{"key":"ref61","article-title":"Hi Robot: Open-ended instruction following with hierarchical vision-language-action models","author":"Xiaoyang Shi","year":"2025","journal-title":"arXiv:2502.19417"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref63","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv:2104.13921"},{"key":"ref64","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11311990.pdf?arnumber=11311990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:45:20Z","timestamp":1767206720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11311990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3647727","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}