外观
论文arXiv 2608.151752 个月前
LAPF：使用 UAVScenes 数据集的基于 LLM-Agent 的路径查找器
原文链接：LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset（arXiv 2608.15175 · 发布日期：2026-08-15）
LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset
针对复杂户外UAV自主导航泛化与适应不足，LAPF以闭环认知架构融合感知、记忆、规划和动作，并在开放场地与注入障碍场景验证。
核心要点
- 现有优化、ML和RL方法依赖预定义模型或任务训练，LLM辅助方法仍缺少充分的智能体功能。
- LAPF将感知、记忆、规划和动作模块整合为闭环认知架构，用于城镇尺度户外UAV导航。
- 该智能体利用既往导航经验和CoT推理，将检测到的危险关联到有界纠正动作，并动态细化航点。
- 三次独立试验显示，LAPF相对CoT prompting缩短路径，并在两类场景中保持近目标稳定且零clamp事件。
验证范围与局限：验证范围限于每种方法三次独立试验，场景为开放场地与注入障碍场景。
英文摘要 (Abstract)
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.
作者：Yousef Emami, Mohammadhossein Homaei, Hao Zhou, Miguel Gutiérrez Gaitán, Atefeh Hajijamali Arani, Rui Zhang
来源
本页事实对应的公开页面，以原文为准。