LAPF：基于大语言模型智能体的路径查找器，使用UAVScenes数据集
LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset
AI总结：
本文提出基于LLM智能体的LAPF框架，整合多模块构建闭环认知架构，在城镇级无人机导航中实现了更优路径效率，且无钳位事件，性能优于CoT提示方法。
AI中文摘要：
无人机（UAV）正越来越多地被部署在复杂室外环境中执行自主导航任务，这类环境中的动态条件和任务需求要求智能系统具备自适应决策能力。现有的基于优化、机器学习（ML）和强化学习（RL）的方法往往依赖预定义模型或特定任务的训练，限制了其在不确定场景中的泛化性和适应性。近期的大语言模型（LLM）辅助方法展现出了良好的推理能力，但仍受限于智能体功能不足，包括记忆、规划和工具交互能力欠缺等问题。本文提出了一种基于大语言模型智能体的路径查找器（LAPF）框架，用于城镇级室外环境中的无人机自主导航。LAPF通过将感知、记忆、规划和动作模块整合到闭环认知架构中，扩展了LLM辅助导航的能力。该智能体利用先前的导航经验，执行思维链（CoT）推理，将每个检测到的危险与有界修正动作关联起来，并根据环境动态细化航点决策。每种方法进行三次独立试验，结果显示，LAPF的平均路径长度分别为512.83米和506.37米，而直线最优路径为497.33米；与思维链（CoT）提示方法相比，路径长度分别减少了17.2%和15.6%，在开阔场地和注入障碍物的场景中，绝对路径效率分别达到97.1%和98.1%。此外，LAPF是所有被评估方法中唯一能将每个检测到的危险与有界、度量中立的修正动作关联，同时保持接近目标的稳定性，在两种场景中均未出现钳位事件，而CoT提示方法的钳位事件则从9.7次增加到14.0次。
英文摘要：
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.
