{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T22:21:36Z","timestamp":1771366896728,"version":"3.50.1"},"reference-count":20,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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","award":["52405029"],"award-info":[{"award-number":["52405029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"science and technology commission of Shanghai municipality","doi-asserted-by":"publisher","award":["24511103400"],"award-info":[{"award-number":["24511103400"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/lra.2026.3662582","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:09:14Z","timestamp":1770671354000},"page":"3883-3890","source":"Crossref","is-referenced-by-count":0,"title":["HiMRAG: Hierarchical Multimodal Retrieval-Augmented Generation for Robot Task Planning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6015-7275","authenticated-orcid":false,"given":"Zhuoyi","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9771-3489","authenticated-orcid":false,"given":"Yixin","family":"Han","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renjun","family":"Li","sequence":"additional","affiliation":[{"name":"Rosiwit Technology Company, Ltd, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2565-9883","authenticated-orcid":false,"given":"Xiao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561548"},{"key":"ref2","article-title":"Task and motion planning in hierarchical 3D scene graphs","author":"Ray","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3112879"},{"key":"ref4","first-page":"1317","article-title":"Regression planning networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3630032"},{"key":"ref6","article-title":"SayPlan: Grounding large language models using 3D scene graphs for scalable task planning","author":"Rana","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610981"},{"key":"ref8","article-title":"Look before you leap: Unveiling the power of GPT-4V in robotic vision-language planning","author":"Hu","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO64047.2024.10907585"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i14.33610"},{"key":"ref11","article-title":"Plan-seq-learn: Language model guided RL for solving long horizon robotics tasks","author":"Dalal","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342363"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3441495"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01703"},{"key":"ref15","article-title":"Embodied-RAG: General non-parametric embodied memory for retrieval and generation","author":"Xie","year":"2024"},{"key":"ref16","article-title":"RAP: Retrieval-augmented planning with contextual memory for multimodal LLM agents","author":"Kagaya","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680661"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.442"},{"key":"ref19","article-title":"LLM-empowered embodied agent for memory-augmented task planning in household robotics","author":"Glocker","year":"2025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128684"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11359420\/11373890.pdf?arnumber=11373890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T21:10:21Z","timestamp":1771362621000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11373890\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":20,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3662582","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}