arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.17840cs.ROcs.CL
收藏

Statler:面向具身推理的状态维持语言模型

Statler: State-Maintaining Language Models for Embodied Reasoning

Toyota Technological Institute at Chicago(芝加哥丰田理工学院);Fudan University(复旦大学);University of Chicago(芝加哥大学)

Takuma Yoneda, Jiading Fang, Peng Li, Huanyu Zhang, Tianchong Jiang, Shengjie Lin, Ben Picker, David Yunis, Hongyuan Mei, Matthew R. Walter

AI总结:

针对大语言模型助力机器人规划的现有研究局限,本文提出Statler框架,通过让大语言模型维护不可观测世界状态的估计并据此决策,在多项规划任务上优于强基线,具备长时序规划拓展潜力。

摘要:

利用大语言模型赋予智能机器人复杂推理能力已成为研究热点。现有工作侧重利用大语言模型对自身动作与观测历史进行推理的能力。本文探索了大语言模型助力机器人规划的一个新维度。具体而言,我们提出Statler框架,该框架通过提示大语言模型维护对通常不可观测的世界状态的估计,并在执行新动作时跟踪其状态转变。随后,该框架将每个动作的决策建立在当前世界状态的估计之上。尽管概念简单,我们的Statler框架在多项机器人规划任务上显著优于强基线方法(如Code-as-Policies)。此外,它具备拓展至更具挑战性的长时序规划任务的潜在优势。

英文摘要:

There has been a significant research interest in employing large language models to empower intelligent robots with complex reasoning. Existing work focuses on harnessing their abilities to reason about the histories of their actions and observations. In this paper, we explore a new dimension in which large language models may benefit robotics planning. In particular, we propose Statler, a framework in which large language models are prompted to maintain an estimate of the world state, which are often unobservable, and track its transition as new actions are taken. Our framework then conditions each action on the estimate of the current world state. Despite being conceptually simple, our Statler framework significantly outperforms strong competing methods (e.g., Code-as-Policies) on several robot planning tasks. Additionally, it has the potential advantage of scaling up to more challenging long-horizon planning tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑