{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T18:45:58Z","timestamp":1766515558460,"version":"3.32.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802251","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"12040-12047","source":"Crossref","is-referenced-by-count":2,"title":["EMPOWER: Embodied Multi-role Open-vocabulary Planning with Online Grounding and Execution"],"prefix":"10.1109","author":[{"given":"Francesco","family":"Argenziano","sequence":"first","affiliation":[{"name":"University of Rome \"La Sapienza\",Automation and Management Engineering,Department of Computer,Rome,Italy,00181"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michele","family":"Brienza","sequence":"additional","affiliation":[{"name":"University of Rome \"La Sapienza\",Automation and Management Engineering,Department of Computer,Rome,Italy,00181"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincenzo","family":"Suriani","sequence":"additional","affiliation":[{"name":"University of Basilicata,School of Engineering,Potenza,Italy,85100"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Nardi","sequence":"additional","affiliation":[{"name":"University of Rome \"La Sapienza\",Automation and Management Engineering,Department of Computer,Rome,Italy,00181"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Domenico D.","family":"Bloisi","sequence":"additional","affiliation":[{"name":"International University of Rome UNINT,Rome,Italy,00147"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"On the opportunities and risks of foundation models","year":"2021","author":"Bommasani","key":"ref1"},{"key":"ref2","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"article-title":"Language models are few-shot learners","year":"2020","author":"Brown","key":"ref4"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref5"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref8","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International Conference on Machine Learning","author":"Huang"},{"article-title":"Multi-agent collaboration: Harnessing the power of intelligent llm agents","year":"2023","author":"Talebirad","key":"ref9"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.3233\/FAIA240916","article-title":"Multi-agent planning using visual language models","author":"Brienza","year":"2024"},{"year":"2024","key":"ref11","article-title":"Gpt-4 technical report"},{"article-title":"Gpt-4v(ision) system card","year":"2023","author":"Brienza","key":"ref12"},{"article-title":"Visual instruction tuning","year":"2023","author":"Liu","key":"ref13"},{"year":"2023","key":"ref14","article-title":"Gemini: A family of highly capable multimodal models"},{"key":"ref15","first-page":"492","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Conference on robot learning","author":"Shah"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341488"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3610978.3640723"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cac59555.2023.10450432"},{"article-title":"Do as i can, not as i say: Grounding language in robotic affordances","year":"2022","author":"Ahn","key":"ref19"},{"article-title":"Palm-e: An embodied multimodal language model","year":"2023","author":"Driess","key":"ref20"},{"article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable task planning","year":"2023","author":"Rana","key":"ref21"},{"journal-title":"Can an embodied agent find your\u201d cat-shaped mug\"? llm-guided exploration for zero-shot object navigation","year":"2023","author":"Dorbala","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610443"},{"article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yuksekgonul","key":"ref24"},{"article-title":"Attention is all you need","year":"2023","author":"Vaswani","key":"ref25"},{"article-title":"Rt-1: Robotics transformer for real-world control at scale","year":"2022","author":"Brohan","key":"ref26"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref27"},{"article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","year":"2023","author":"Padalkar","key":"ref28"},{"article-title":"\"overview of embodied artificial intelligence","year":"2021","author":"Bermudez","key":"ref29"},{"article-title":"Tree of thoughts: Deliberate problem solving with large language models","year":"2023","author":"Yao","key":"ref30"},{"article-title":"Autogen: Enabling next-gen llm applications via multi-agent conversation framework","year":"2023","author":"Wu","key":"ref31"},{"article-title":"Llm harmony: Multi-agent communication for problem solving","year":"2024","author":"Rasal","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06647-8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-60615-1_7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/s24051687"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"article-title":"Open-vocabulary object detection via vision and language knowledge distillation","year":"2021","author":"Gu","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"article-title":"Conceptgraphs: Open-vocabulary 3d scene graphs for perception and planning","year":"2023","author":"Gu","key":"ref43"},{"article-title":"Roboexp: Action-conditioned scene graph via interactive exploration for robotic manipulation","year":"2024","author":"Jiang","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00782"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3447772"},{"key":"ref48","article-title":"spaCy 2: Natural language under-standing with Bloom embeddings, convolutional neural networks and incremental parsing","author":"Honnibal","year":"2018","journal-title":"To appear"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56608-5_31"},{"article-title":"Reducing the barrier to entry of complex robotic software: a moveit! case study","year":"2014","author":"Coleman","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802251.pdf?arnumber=10802251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:00:00Z","timestamp":1735196400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802251\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802251","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}