{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:51:06Z","timestamp":1784904666646,"version":"3.55.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610981","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"14054-14061","source":"Crossref","is-referenced-by-count":30,"title":["Interactive Planning Using Large Language Models for Partially Observable Robotic Tasks"],"prefix":"10.1109","author":[{"given":"Lingfeng","family":"Sun","sequence":"first","affiliation":[{"name":"UC Berkeley,Mechanical Systems Control Lab,Berkeley,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Devesh K.","family":"Jha","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories,Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chiori","family":"Hori","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories,Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siddarth","family":"Jain","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories,Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Radu","family":"Corcodel","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories,Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinghao","family":"Zhu","sequence":"additional","affiliation":[{"name":"UC Berkeley,Mechanical Systems Control Lab,Berkeley,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"UC Berkeley,Mechanical Systems Control Lab,Berkeley,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diego","family":"Romeres","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories,Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref2","article-title":"Palm 2 technical report","author":"Anil","year":"2023"},{"key":"ref3","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref4","article-title":"Chatgpt for robotics: Design principles and model abilities","volume-title":"Microsoft, Tech. Rep. MSR-TR-2023-8","author":"Vemprala","year":"2023"},{"key":"ref5","article-title":"Do as i can, not as i say: Grounding language in roboticaffordances","author":"Ahn","year":"2022"},{"key":"ref6","article-title":"Language to rewards for robotic skill synthesis","author":"Yu","year":"2023"},{"key":"ref7","article-title":"Pre-trained language models for interactive decision-making","author":"Li","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"issue":"1","key":"ref9","first-page":"99","article-title":"Planning and acting in partially observable stochastic domains","volume-title":"Artificial Intelligence","volume":"101","author":"Kaelbling","year":"1998"},{"key":"ref10","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022"},{"key":"ref11","article-title":"Palme: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref12","article-title":"Self-instruct: Aligning language model with self generated instructions","author":"Wang","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref14","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023"},{"key":"ref15","first-page":"1713","article-title":"Skill induction and planning with latent language","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Sharma"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342169"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref19","article-title":"Autotamp: Autoregressive task and motion planning with llms as translators and checkers","author":"Chen","year":"2023"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"4412","DOI":"10.18653\/v1\/2020.findings-emnlp.395","article-title":"Visually-grounded planning without vision: Language models infer detailed plans from high-level instructions","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Jansen","year":"2020"},{"key":"ref21","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023"},{"key":"ref22","article-title":"Roco: Dialectic multi-robot collaboration with large language models","author":"Mandi","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3578623"},{"key":"ref24","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"ArXiv preprint","volume":"abs\/2210.03629","author":"Yao","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.065"},{"key":"ref26","article-title":"Reflect: Summarizing robot experiences for failure explanation and correction","author":"Liu","year":"2023"},{"key":"ref27","article-title":"Robots that ask for help: Uncertainty alignment for large language model planners","author":"Ren","year":"2023"},{"key":"ref28","article-title":"Asking before action: Gather information in embodied decision making with language models","author":"Chen","year":"2023"},{"key":"ref29","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref30","article-title":"Stanford alpaca: An instructionfollowing llama model","author":"Taori","year":"2023"},{"key":"ref31","article-title":"Gorilla: Large language model connected with massive apis","author":"Patil","year":"2023"},{"key":"ref32","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face","author":"Shen","year":"2023"},{"key":"ref33","article-title":"Toolllm: Facilitating large language models to master 16000+ real-world apis","author":"Qin","year":"2023"},{"key":"ref34","article-title":"Toolalpaca: Generalized tool learning for language models with 3000 simulated cases","author":"Tang","year":"2023"},{"key":"ref35","article-title":"Auto-gpt for online decision making: Benchmarks and additional opinions","author":"Yang","year":"2023"},{"key":"ref36","article-title":"Large language models are zero-shot reasoners","author":"Kojima","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.441"},{"key":"ref38","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","author":"Hu"},{"key":"ref39","article-title":"Llama-adapter v2: Parameterefficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref40","article-title":"Code llama: Open foundation models for code","author":"Rozi\u00e8re","year":"2023"},{"key":"ref41","article-title":"Bridgedata v2: A dataset for robot learning at scale","author":"Walke","year":"2023"},{"key":"ref42","article-title":"Roboagent: Towards sample efficient robot manipulation with semantic augmentations and action chunking","author":"Bharadhwaj","year":"2023","journal-title":"arxiv"},{"key":"ref43","article-title":"Rh20t: A robotic dataset for learning diverse skills in one-shot","author":"Fang","year":"2023"},{"key":"ref44","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.830"},{"key":"ref46","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979561"},{"key":"ref48","article-title":"Minigpt4: Enhancing vision-language understanding with advanced large language models","volume-title":"ArXiv preprint","volume":"abs\/2304.10592","author":"Zhu","year":"2023"},{"key":"ref49","article-title":"Visual instruction tuning","volume-title":"ArXiv preprint","volume":"abs\/2304.08485","author":"Liu","year":"2023"},{"key":"ref50","article-title":"Homerobot: Open vocab mobile manipulation","author":"Yenamandra","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610981.pdf?arnumber=10610981","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:59:56Z","timestamp":1723269596000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610981\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610981","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}