Dadu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipelines

doi:10.1002/rob.70120

CSpace

	Dadu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipelines
	Sun, Wenhao 1,2; Hou, Sai 3; Wang, Zixuan 2,4; Yu, Bo 5; Liu, Shaoshan 5; Yang, Xu 3; Liang, Shuai 1; Gan, Yiming 1; Han, Yinhe 1
	2025-12-10
发表期刊	JOURNAL OF FIELD ROBOTICS
ISSN	1556-4959
页码	24
摘要	Performing complex tasks in open environments remains challenging for robots, even when using large language models (LLMs) as the core planner. Many LLM-based planners are inefficient due to their large number of parameters and prone to inaccuracies because they operate in open-loop systems. We think the reason is that only applying LLMs as planners is insufficient. In this study, we propose Dadu-Embodied (Dadu-E), a robust closed-loop planning framework for embodied Artificial Intelligence (AI) robots. Specifically, Dadu-E is equipped with a relatively lightweight LLM, a set of encapsulated robot skill instructions, a robust feedback system, and memory augmentation. Together, these components enable Dadu-E to (i) actively perceive and adapt to dynamic environments, (ii) optimize computational costs while maintaining high performance, and (iii) recover from execution failures using its memory and feedback mechanisms. By seamlessly integrating a lightweight LLM, encapsulated robot skill instructions, closed-loop feedback, and memory augmentation, Dadu-E establishes a robust and extensible embodied AI robotic framework capable of stable operation in real-world environments. Extensive experiments on real-world and simulated tasks show that Dadu-E achieves task success rates comparable to embodied AI robots with larger models as planners like COME-Robot, while reducing computational requirements by . Users are encouraged to explore our system at https://rlc-lab.github.io/dadu-e/.
关键词	closed-loop planning large language models memory augmentation robotic planning
DOI	10.1002/rob.70120
收录类别	SCI
语种	英语
WOS研究方向	Robotics
WOS类目	Robotics
WOS记录号	WOS:001634516000001
出版者	WILEY
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42936
专题	中国科学院计算技术研究所
通讯作者	Yu, Bo; Yang, Xu; Gan, Yiming; Han, Yinhe
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Chinese Acad Sci ICT, Beijing, Peoples R China 2.Univ Chinese Acad Sci UCAS, Sch Comp Sci & Technol, Sch Artificial Intelligence, Beijing, Peoples R China 3.Beijing Inst Technol BIT, Sch Comp Sci & Technol, Beijing, Peoples R China 4.Chinese Acad Sci CASIA, Inst Automat, Beijing, Peoples R China 5.Shenzhen Inst Artificial Intelligence & Robot Soc, Embodied AI Ctr, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Sun, Wenhao,Hou, Sai,Wang, Zixuan,et al. Dadu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipelines[J]. JOURNAL OF FIELD ROBOTICS,2025:24.
APA	Sun, Wenhao.,Hou, Sai.,Wang, Zixuan.,Yu, Bo.,Liu, Shaoshan.,...&Han, Yinhe.(2025).Dadu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipelines.JOURNAL OF FIELD ROBOTICS,24.
MLA	Sun, Wenhao,et al."Dadu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipelines".JOURNAL OF FIELD ROBOTICS (2025):24.