Text2Reaction : Enabling Reactive Task Planning Using Large Language Models

doi:10.1109/LRA.2024.3371223

CSpace

	Text2Reaction : Enabling Reactive Task Planning Using Large Language Models
	Yang, Zejun 1,2; Ning, Li 1,2; Wang, Haitao 1,3; Jiang, Tianyu 1,3; Zhang, Shaolin 1,3; Cui, Shaowei 1,3; Jiang, Hao 1,2; Li, Chunpeng 1,2; Wang, Shuo 1,3; Wang, Zhaoqi 1,2
	2024-05-01
发表期刊	IEEE ROBOTICS AND AUTOMATION LETTERS
ISSN	2377-3766
卷号	9 期号:5 页码:4003-4010
摘要	To complete tasks in dynamic environments, robots need to timely update their plans to react to environment changes. Traditional stripe-like or learning-based planners struggle to achieve this due to their high reliance on meticulously predefined planning rules or labeled data. Fortunately, recent works find that Large Language Models (LLMs) can be effectively prompted to solve planning problems. Thus, we investigate the strategies for LLMs to master reactive planning problems without complex definitions and extra training. We propose Text2Reaction, an LLM-based framework enabling robots to continuously reason and update plans according to the latest environment changes. Inspired from human's step-by-step re-planning process, we present the Re-planning Prompt, which informs LLMs the basic principles of re-planning and fosters the gradual development of a current plan to a new one in a three-hop reasoning manner-cause analysis, consequence inference, and plan adjustment. In addition, Text2Reaction is designed to first generate an initial plan based on the task description before execution, allowing for subsequent iterative updates of this plan. We demonstrate the superior performance of Text2Reaction over prior works in reacting to various environment changes and completing varied tasks. In addition, we validate the reliability of our re-planning prompt through ablation experiments and its capability when deployed in real-world robots, enabling continuous reasoning in the face of diverse changes until the user instructions are successfully completed.
关键词	Planning under uncertainty AI-based methods learning from demonstration
DOI	10.1109/LRA.2024.3371223
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China
WOS研究方向	Robotics
WOS类目	Robotics
WOS记录号	WOS:001189843900003
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38759
专题	中国科学院计算技术研究所
通讯作者	Cui, Shaowei; Jiang, Hao
作者单位	1.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Yang, Zejun,Ning, Li,Wang, Haitao,et al. Text2Reaction : Enabling Reactive Task Planning Using Large Language Models[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2024,9(5):4003-4010.
APA	Yang, Zejun.,Ning, Li.,Wang, Haitao.,Jiang, Tianyu.,Zhang, Shaolin.,...&Wang, Zhaoqi.(2024).Text2Reaction : Enabling Reactive Task Planning Using Large Language Models.IEEE ROBOTICS AND AUTOMATION LETTERS,9(5),4003-4010.
MLA	Yang, Zejun,et al."Text2Reaction : Enabling Reactive Task Planning Using Large Language Models".IEEE ROBOTICS AND AUTOMATION LETTERS 9.5(2024):4003-4010.