Language models (LMs) have demonstrated their capability in possessing commonsense knowledge of the physical world, a crucial aspect of performing tasks in everyday life. However, it remains unclear **whether LMs have the capacity to generate grounded, executable plans for embodied tasks.** This is a challenging task as LMs lack the ability to perceive the environment through vision and feedback from the physical environment. In this paper, we address this important research question and present the first investigation into the topic. Our novel problem formulation, named **G-PlanET**, inputs a high-level goal and a data table about objects in a specific environment, and then outputs a step-by-step actionable plan for a robotic agent to follow. To facilitate the study, we establish an **evaluation protocol** and design a dedicated metric to assess the quality of the plans. Our experiments demonstrate that the use of tables for encoding the environment and an iterative decoding strategy can significantly enhance the LMs' ability in grounded planning. Our analysis also reveals interesting and non-trivial findings.

翻译：语言模型（LMs）已展现出具备物理世界常识性知识的能力，这是其执行日常任务的关键要素。然而，**语言模型是否能够为具身任务生成基于环境且可执行的规划，** 仍是一个未解之谜。这项任务极具挑战性，因为语言模型缺乏通过视觉感知环境及接收物理环境反馈的能力。本文旨在探索这一重要研究问题，并首次对该课题展开系统性研究。我们提出了一种全新的问题形式化框架——**G-PlanET**，该框架以高层目标及特定环境中物体的数据表作为输入，输出供机器人代理逐步执行的行动方案。为便于研究，我们构建了一套**评估协议**并设计了专用指标来评估规划质量。实验表明，采用表格对环境进行编码，并结合迭代解码策略，能显著提升语言模型在基础规划中的能力。此外，我们的分析还揭示了若干有趣且非平凡的研究发现。