Statler: 身体性推論のための状態維持型言語モデル
Statler: State-Maintaining Language Models for Embodied Reasoning
大規模言語モデルに世界状態の推定とその遷移を維持させ、その推定に基づいてロボットの行動を決定するフレームワークStatlerを提案し、複数のロボット計画タスクで既存手法を上回る性能を示した。
著者: Takuma Yoneda, Jiading Fang, Peng Li, Huanyu Zhang, Tianchong Jiang, Shengjie Lin, Ben Picker, David Yunis, Hongyuan Mei, Matthew R. Walter
分類: cs.RO, cs.CL
原文アブストラクト
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.
