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. We release our code at https://github.com/ripl/statler

翻译：近年来，利用大型语言模型赋予智能机器人复杂推理能力的研究备受关注。现有工作侧重于利用它们推理自身动作与观测历史的能力。本文探索了大型语言模型可能助力机器人规划的新维度。具体而言，我们提出Statler框架，该框架引导大型语言模型维护对世界状态（通常不可观测）的估计，并追踪新动作执行后状态的转移。我们框架中的每个动作均基于当前世界状态的估计值进行条件化。尽管概念简单，我们的Statler框架在多个机器人规划任务上显著优于强竞争方法（例如Code-as-Policies）。此外，该方法在扩展到更具挑战性的长时域规划任务方面具有潜在优势。我们已在https://github.com/ripl/statler 公开发布代码。