{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T18:15:13Z","timestamp":1779387313059,"version":"3.53.1"},"reference-count":36,"publisher":"Institution of Engineering and Technology (IET)","issue":"2","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFA1008500"],"award-info":[{"award-number":["2023YFA1008500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016804","name":"Natural Science Foundation of Shenzhen Municipality","doi-asserted-by":"publisher","award":["RCBS20231211090749086"],"award-info":[{"award-number":["RCBS20231211090749086"]}],"id":[{"id":"10.13039\/100016804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2035"],"award-info":[{"award-number":["U22B2035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["CAAI Trans on Intel Tech"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>To enable autonomous operations in complex industrial environments, this paper proposes retrieval\u2010augmented generation with large language models for robotic operations (RAGLRO), a robotic framework specifically designed for power switchgear operation tasks. The system integrates multimodal perception with high\u2010level semantic reasoning and task\u2010level action generation. A depth camera captures the environmental context, which is processed by visual modules to perform object detection and pose detection. The perception outputs are formulated into structured prompts and provided to a large language model (LLM) equipped with a retrieval\u2010augmented generation (RAG) mechanism. The RAG component enables the LLM to dynamically access a task\u2010specific knowledge base, including operation manuals, safety protocols and historical mission data, thereby enhancing contextual understanding and reasoning precision. Based on the retrieved knowledge and current environmental perception, the LLM selects and sequences callable action functions from a predefined robotic action library to generate executable robot control commands. A dedicated dataset for power switchgear operations is also constructed to support robust visual perception, containing annotated images for object detection and pose detection tasks. Experimental results demonstrate that RAGLRO achieves high task success rates and strong adaptability in real\u2010world power maintenance scenarios, validating the effectiveness of integrating multimodal perception, LLM\u2010based reasoning and RAG\u2010grounded task planning within a unified robotic control framework.<\/jats:p>","DOI":"10.1049\/cit2.70105","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T16:52:13Z","timestamp":1769791933000},"page":"385-395","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RAGLRO: Retrieval\u2010Augmented Generation With Large Language Models for Robotic Operations"],"prefix":"10.1049","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8289-5942","authenticated-orcid":false,"given":"Wenrui","family":"Wang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology  Harbin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Penghong","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology  Harbin China"},{"name":"Harbin Institute of Technology Suzhou Research Institute  Suzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[{"name":"Faculty of Computational Mathematics and Cybernetics Shenzhen MSU\u2010BIT University  Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology  Harbin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pinhao","family":"Song","sequence":"additional","affiliation":[{"name":"Research Unit Robotics Automation and Mechatronics Department of Mechanical Engineering KU Leuven Leuven  Flanders Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oleg","family":"Cherkasov","sequence":"additional","affiliation":[{"name":"Faculty of Mechanics and Mathematics Lomonosov Moscow State University Moscow  Moscow Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology  Harbin China"},{"name":"Harbin Institute of Technology Suzhou Research Institute  Suzhou China"},{"name":"China Peng Cheng Laboratory Shenzhen Peng Cheng Laboratory  Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"265","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/mra.2015.2460931"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2024.100651"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2009.2022424"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/mra.2007.339624"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.2015\u2010sep\u20106"},{"key":"e_1_2_9_7_1","unstructured":"J.Achiam S.Adler S.Agarwal et\u00a0al. \u201cGpt\u20104 Technical Report \u201d arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_2_9_8_1","unstructured":"TeamG. L. M. A.Zeng B.Xu et\u00a0al. \u201cChatglm: A Family of Large Language Models From glm\u2010130b to glm\u20104 all Tools \u201d arXiv preprint arXiv:2406.12793 (2024)."},{"key":"e_1_2_9_9_1","unstructured":"H.Touvron T.Lavril G.Izacard et\u00a0al. \u201cLlama: Open and Efficient Foundation Language Models \u201d arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_2_9_10_1","unstructured":"J.Yao W.Xu J.Lian X.Wang X.Yi andX.Xie \u201cKnowledge Plugins: Enhancing Large Language Models for Domain\u2010Specific Recommendations \u201d arXiv preprint arXiv:2311.10779 (2023)."},{"key":"e_1_2_9_11_1","doi-asserted-by":"crossref","unstructured":"X.Gong M.Liu andX.Chen.Large Language Models With Knowledge Domain Partitioning for Specialized Domain Knowledge Concentration (2024).","DOI":"10.31219\/osf.io\/srgpx"},{"key":"e_1_2_9_12_1","doi-asserted-by":"crossref","unstructured":"H.Li Q.Ai J.Chen et\u00a0al. \u201cBlade: Enhancing Black\u2010Box Large Language Models With Small Domain\u2010Specific Models \u201d arXiv preprint arXiv:2403.18365 (2024).","DOI":"10.1609\/aaai.v39i23.34620"},{"key":"e_1_2_9_13_1","unstructured":"C.Wang X.Liu Y.Yue et\u00a0al. \u201cSurvey on Factuality in Large Language Models: Knowledge Retrieval and Domain\u2010Specificity \u201d arXiv preprint arXiv:2310.07521 (2023)."},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1996.506522"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"e_1_2_9_16_1","first-page":"OS15","volume-title":"Proceedings of International Conference on Artificial Life & Robotics (ICAROB2024)","author":"Yamao K.","year":"2024"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689050.3704424"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2024.09.178"},{"key":"e_1_2_9_19_1","first-page":"445","volume-title":"International Conference on Case\u2010based Reasoning","author":"Wiratunga N.","year":"2024"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.01.135"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3456893"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3114399"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371\u2010023\u201003097\u20101"},{"key":"e_1_2_9_26_1","first-page":"445","volume-title":"Photonics","author":"Duan J.","year":"2024"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00346"},{"key":"e_1_2_9_28_1","doi-asserted-by":"crossref","unstructured":"YuXiang T.Schmidt V.Narayanan andD.Fox \u201cPosecnn: A Convolutional Neural Network for 6d Object Pose Estimation in Cluttered Scenes \u201d arXiv preprint arXiv:1711.00199 (2017).","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3550145"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1108\/17563780911005845"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907656"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2019.03.121"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10845\u2010021\u201001867\u2010z"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2023.3296166"}],"container-title":["CAAI Transactions on Intelligence Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70105","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cit2.70105","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:56:19Z","timestamp":1779386179000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cit2.70105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,30]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1049\/cit2.70105"],"URL":"https:\/\/doi.org\/10.1049\/cit2.70105","archive":["Portico"],"relation":{},"ISSN":["2468-6557","2468-2322"],"issn-type":[{"value":"2468-6557","type":"print"},{"value":"2468-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,30]]},"assertion":[{"value":"2025-06-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}