This work explores the capacity of large language models (LLMs) to address
problems at the intersection of spatial planning and natural language
interfaces for navigation.Our focus is on following relatively complex
instructions that are more akin to natural conversation than traditional
explicit procedural directives seen in robotics. Unlike most prior work, where
navigation directives are provided as imperative commands (e.g., go to the
fridge), we examine implicit directives within conversational interactions. We
leverage the 3D simulator AI2Thor to create complex and repeatable scenarios at
scale, and augment it by adding complex language queries for 40 object types.
We demonstrate that a robot can better parse descriptive language queries than
existing methods by using an LLM to interpret the user interaction in the
context of a list of the objects in the scene.

该研究通过大型语言模型（LLMs）探索了空间规划和自然语言界面与导航的交叉问题。我们关注的是遵循与传统机器人指令不同、更类似于自然对话的相对复杂的指令。与先前的大多数工作不同的是，我们研究了对话交互中的隐式指令。通过利用 3D 模拟器 AI2Thor 在规模上创建复杂且可重复的场景，并通过为 40 种对象类型增加复杂的语言查询来扩充它。我们证明了通过使用 LLM 将用户交互解释为场景中对象列表的上下文，机器人能够更好地解析描述性语言查询。