{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T07:13:46Z","timestamp":1777187626703,"version":"3.51.4"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"20","license":[{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"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":["12373107"],"award-info":[{"award-number":["12373107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,10,15]]},"DOI":"10.1109\/jiot.2025.3590433","type":"journal-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T18:44:39Z","timestamp":1753296279000},"page":"41864-41879","source":"Crossref","is-referenced-by-count":1,"title":["Embodied Assistant: Robot Mobility Operations Guided by Open Vocabulary in Open Environments Utilizing LLM"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1320-0605","authenticated-orcid":false,"given":"Yanan","family":"Guo","sequence":"first","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanshu","family":"Ni","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7753-7656","authenticated-orcid":false,"given":"Jing","family":"Jin","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dandan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3198-1927","authenticated-orcid":false,"given":"Yi","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21570"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2023.1084000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3295255"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3459918"},{"key":"ref5","first-page":"706","article-title":"A persistent spatial semantic representation for high-level natural language instruction execution","volume-title":"Proc. Conf. Robot Learn.","author":"Blukis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103903"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref8","first-page":"991","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","volume-title":"Proc. Conf. Robot Learn.","author":"Jang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-101119-071628"},{"issue":"8","key":"ref11","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref12","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref13","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang"},{"key":"ref14","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref15","article-title":"React: Synergizing reasoning and acting in language models","author":"Yao","year":"2022","journal-title":"arXiv:2210.03629"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref17","article-title":"Reflect: Summarizing robot experiences for failure explanation and correction","author":"Liu","year":"2023","journal-title":"arXiv:2306.15724"},{"key":"ref18","article-title":"Ok-robot: What really matters in integrating open-knowledge models for robotics","author":"Liu","year":"2024","journal-title":"arXiv:2401.12202"},{"key":"ref19","article-title":"Look before you leap: Unveiling the power of GPT-4V in robotic vision-language planning","author":"Hu","year":"2023","journal-title":"arXiv:2311.17842"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63223-5_28"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2010.06.019"},{"key":"ref22","article-title":"RePLan: Robotic replanning with perception and language models","author":"Skreta","year":"2024","journal-title":"arXiv:2401.04157"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(98)00067-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/math11163489"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812344"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636554"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3336109"},{"key":"ref29","first-page":"23634","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zellers"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.373"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28572-1_3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3193254"},{"key":"ref33","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Thomason"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.065"},{"key":"ref35","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561983"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/daed_a_01902"},{"key":"ref38","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref40","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023","journal-title":"arXiv:2305.16291"},{"key":"ref41","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"arXiv:2307.05973"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3346800"},{"key":"ref43","first-page":"492","article-title":"LM-Nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. Conf. Robot Learn.","author":"Shah"},{"key":"ref44","article-title":"LLM as a robotic brain: Unifying egocentric memory and control","author":"Mai","year":"2023","journal-title":"arXiv:2304.09349"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref47","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022","journal-title":"arXiv:2207.05608"},{"key":"ref48","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref50","article-title":"MOSAIC: A modular system for assistive and interactive cooking","author":"Wang","year":"2024","journal-title":"arXiv:2402.18796"},{"key":"ref51","article-title":"Closed-loop open-vocabulary mobile manipulation with GPT-4V","author":"Zhi","year":"2024","journal-title":"arXiv:2404.10220"},{"key":"ref52","article-title":"VADER: Visual affordance detection and error recovery for multi robot human collaboration","author":"Ahn","year":"2024","journal-title":"arXiv:2405.16021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref55","article-title":"The dawn of LMMs: Preliminary explorations with GPT-4V (ision)","author":"Yang","year":"2023","journal-title":"arXiv:2309.17421"},{"key":"ref56","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref58","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv:2306.14289"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref60","volume-title":"Model card and evaluations for claude models","author":"Anthropic","year":"2023"},{"key":"ref61","volume-title":"OpenAI O3-mini","year":"2025"},{"key":"ref62","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref63","volume-title":"The Claude 3 model family: Opus, Sonnet, Haiku","year":"2024"},{"key":"ref64","volume-title":"Hello GPT-4o","year":"2024"},{"key":"ref65","volume-title":"Introducing Gemini 2.0: Our new AI model for the agentic era","author":"DeepMind","year":"2024"},{"key":"ref66","volume-title":"Introducing Claude 3.5 Sonnet","year":"2024"},{"key":"ref67","volume-title":"Introducing GPT-4o1: Advancements in AI reasoning","year":"2024"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11197149\/11091348.pdf?arnumber=11091348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:55:57Z","timestamp":1760032557000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11091348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":68,"journal-issue":{"issue":"20"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3590433","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,15]]}}}