View in EDS

A robot operating system framework for using large language models in embodied AI.

Saved in:
Bibliographic Details
Title: A robot operating system framework for using large language models in embodied AI.
Authors: Mower, Christopher E., Wan, Yuhui, Yu, Hongzhan, Grosnit, Antoine, Gonzalez-Billandon, Jonas, Zimmer, Matthieu, Liu, Puze, Palenicek, Daniel, Tateo, Davide, Peters, Jan, Qu, Kaixian, Zhang, Mike, Lan, Guowei, Cramariuc, Andrei, Cadena, Cesar, Hutter, Marco, Tian, Guangjian, Zhuang, Yuzhen, Shao, Kun, Quan, Xingyue
Source: Nature Machine Intelligence; Mar2026, Vol. 8 Issue 3, p313-325, 13p
Abstract: Autonomous robots capable of turning natural-language instructions into reliable physical actions remain a central challenge in artificial intelligence. Here we show that connecting a large language model agent to the robot operating system enables a versatile framework for embodied intelligence, and we release the complete implementation as freely available open-source code. The agent automatically translates large language model outputs into robot actions, supports interchangeable execution modes (inline code or behaviour trees), learns new atomic skills via imitation, and continually refines them through automated optimization and reflection from human or environmental feedback. Extensive experiments validate the framework, showcasing robustness, scalability and versatility in diverse scenarios and embodiments, including long-horizon tasks, tabletop rearrangements, dynamic task optimization and remote supervisory control. Moreover, all the results presented in this work were achieved by utilizing open-source pretrained large language models. Mower, Wan et al. introduce ROS-LLM, an open-source system that lets non-experts control robots with natural language, learn new skills from demonstrations and feedback, and automatically tune actions for reliable performance in real-world tasks. [ABSTRACT FROM AUTHOR]
Copyright of Nature Machine Intelligence is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Biomedical Index
Description
Abstract:Autonomous robots capable of turning natural-language instructions into reliable physical actions remain a central challenge in artificial intelligence. Here we show that connecting a large language model agent to the robot operating system enables a versatile framework for embodied intelligence, and we release the complete implementation as freely available open-source code. The agent automatically translates large language model outputs into robot actions, supports interchangeable execution modes (inline code or behaviour trees), learns new atomic skills via imitation, and continually refines them through automated optimization and reflection from human or environmental feedback. Extensive experiments validate the framework, showcasing robustness, scalability and versatility in diverse scenarios and embodiments, including long-horizon tasks, tabletop rearrangements, dynamic task optimization and remote supervisory control. Moreover, all the results presented in this work were achieved by utilizing open-source pretrained large language models. Mower, Wan et al. introduce ROS-LLM, an open-source system that lets non-experts control robots with natural language, learn new skills from demonstrations and feedback, and automatically tune actions for reliable performance in real-world tasks. [ABSTRACT FROM AUTHOR]
ISSN:25225839
DOI:10.1038/s42256-026-01186-z