用大模型做室内导航，能自动理解环境并灵活规划路径。
Research on Navigation Methods Based on LLMs
- 将导航功能拆解为可复用的LLM工具，由大模型统一调度。
- 在模拟环境中实现动态场景下的上下文感知导航，效果显著。
- 适合研究智能机器人、AI助手等需要自主决策的应用场景。
近年来，大型语言模型（LLMs）的引入推动了室内导航领域的突破性进展。传统依赖预构建地图或强化学习的导航方法存在泛化能力差、难以适应动态环境的问题。相比之下，LLMs凭借其出色的语义理解、推理能力及零样本泛化特性，为复杂室内导航任务提供了新范式。本文提出一种基于LLM的导航框架，利用函数调用能力，将大模型置于核心控制位置。方法上，将传统导航功能模块化为可复用的LLM工具，并支持可扩展配置。同时设计了系统性、可迁移的系统提示模板与交互流程，便于不同实现间的快速适配。在PyBullet仿真环境中，针对多种场景的实验验证表明，该方法在动态工具组合与上下文感知导航方面展现出显著潜力与有效性。
原文摘要 · Abstract (English)
In recent years, the field of indoor navigation has witnessed groundbreaking advancements through the integration of Large Language Models (LLMs). Traditional navigation approaches relying on pre-built maps or reinforcement learning exhibit limitations such as poor generalization and limited adaptability to dynamic environments. In contrast, LLMs offer a novel paradigm for complex indoor navigation tasks by leveraging their exceptional semantic comprehension, reasoning capabilities, and zero-shot generalization properties. We propose an LLM-based navigation framework that leverages function calling capabilities, positioning the LLM as the central controller. Our methodology involves modular decomposition of conventional navigation functions into reusable LLM tools with expandable configurations. This is complemented by a systematically designed, transferable system prompt template and interaction workflow that can be easily adapted across different implementations. Experimental validation in PyBullet simulation environments across diverse scenarios demonstrates the substantial potential and effectiveness of our approach, particularly in achieving context-aware navigation through dynamic tool composition.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。