Tag Map：一种用于大型语言模型空间推理与导航的基于文本的地图
Tag Map: A Text-Based Map for Spatial Reasoning and Navigation with Large Language Models
AI总结：
提出一种显式基于文本的地图Tag Map，利用大规模图像识别模型表示数千语义类别并易于与LLM集成，其定位性能与开放词汇地图相当且内存占用降低二到四个数量级，真实机器人实验验证了其有效性。
摘要：
大型语言模型（LLM）已成为机器人利用常识推理生成任务计划的工具。为使LLM生成可执行的计划，必须提供场景上下文，通常通过地图实现。近期工作已从具有固定语义类别的显式地图转向基于可查询嵌入的隐式开放词汇地图，后者能够表示任意语义类别。然而，嵌入是隐式的，无法直接报告场景上下文，需要进一步处理才能与LLM集成。为此，我们提出一种显式的基于文本的地图，它基于大规模图像识别模型构建，能够表示数千个语义类别，并因其基于文本的特性而易于与LLM集成。我们研究了如何定位地图中的实体，并通过评估表明，基于文本的地图定位性能与开放词汇地图相当，但内存使用量减少了二到四个数量级。真实机器人实验演示了利用基于文本的地图对LLM进行接地以解决用户任务的过程。
英文摘要：
Large Language Models (LLM) have emerged as a tool for robots to generate task plans using common sense reasoning. For the LLM to generate actionable plans, scene context must be provided, often through a map. Recent works have shifted from explicit maps with fixed semantic classes to implicit open vocabulary maps based on queryable embeddings capable of representing any semantic class. However, embeddings cannot directly report the scene context as they are implicit, requiring further processing for LLM integration. To address this, we propose an explicit text-based map that can represent thousands of semantic classes while easily integrating with LLMs due to their text-based nature by building upon large-scale image recognition models. We study how entities in our map can be localized and show through evaluations that our text-based map localizations perform comparably to those from open vocabulary maps while using two to four orders of magnitude less memory. Real-robot experiments demonstrate the grounding of an LLM with the text-based map to solve user 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。
