用大模型构建可自主规划路径的无人机导航系统，提升复杂环境适应性。
LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset
- 基于大模型构建闭环认知架构，融合感知、记忆、规划与行动模块。
- 在真实场景中路径长度仅比最优直线长15.6%，效率达98.1%且零碰撞事件。
- 能对每个障碍物动态生成安全应对动作，适合高复杂度户外自主导航任务。
无人飞行器（UAV）在复杂室外环境中日益用于自主导航，动态条件与任务需求要求智能自适应决策。现有基于优化、机器学习和强化学习的方法通常依赖预设模型或特定任务训练，限制了其在不确定场景中的泛化能力。近期的大语言模型（LLM）辅助方法虽具推理潜力，但受限于代理功能不足，如记忆、规划与工具交互能力有限。本文提出一种基于大模型代理的路径规划框架（LAPF），用于城镇规模室外环境下的自主无人机导航。LAPF通过整合感知、记忆、规划与动作模块，构建闭环认知架构。该代理利用过往导航经验，执行思维链（CoT）推理，将每个检测到的障碍物关联至有界纠正动作，并根据环境反馈动态优化航点决策。三次独立实验表明，LAPF在开放场与障碍物注入场景中分别实现512.83米与506.37米的平均路径长度，相较直线最优路径497.33米，路径长度减少17.2%和15.6%，绝对路径效率分别为97.1%与98.1%。此外，LAPF是唯一将每个检测到的障碍物关联至有界、无量纲纠正动作并保持近目标稳定性的方法，两类场景中均实现零夹持事件；而CoT提示法夹持事件从9.7上升至14.0。
原文摘要 · Abstract (English)
Uncrewed aerial vehicles (UAVs) are increasingly deployed for autonomous navigation in complex outdoor environments, where dynamic conditions and mission requirements require intelligent adaptive decision-making. Existing optimization-based, Machine Learning (ML), and Reinforcement Learning (RL) approaches often rely on predefined models or task-specific training, limiting their generalization and adaptability in uncertain scenarios. Recent Large Language Model (LLM)-assisted approaches offer promising reasoning capabilities but remain constrained by limited agentic functionality, including insufficient memory, planning, and tool interaction mechanisms.This paper proposes an LLM-Agent-Based Path Finder (LAPF) framework for autonomous UAV navigation in town-scale outdoor environments. LAPF extends LLM-assisted navigation by integrating perception, memory, planning, and action modules into a closed-loop cognitive architecture. The proposed agent leverages prior navigation experiences, performs Chain-of-Thought (CoT) reasoning, couples each detected hazard to a bounded corrective action, and dynamically refines waypoint decisions based on environmental feedback.The three independent trials per method demonstrate that LAPF achieves mean path lengths of 512.83 m and 506.37 m, compared to the straight-line optimum of 497.33 m, corresponding to path length reductions of 17.2% and 15.6% relative to CoT prompting and absolute path efficiencies of 97.1% and 98.1% in open-field and obstacle-injected scenarios, respectively. Furthermore, LAPF is the only evaluated approach that couples every detected hazard to a bounded, metric-neutral corrective action while maintaining near-goal stability, with zero clamp events in both scenarios, whereas CoT prompting increases from 9.7 to 14.0 events.
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。