用大模型闭环生成无人机代码，提升复杂任务可靠性。
Large Language Model-Driven Closed-Loop UAV Operation with Semantic Observations
- 双模块协同：代码生成+评估，实现动态反馈优化。
- 模拟验证取代实机试错，任务成功率显著提升。
- 适合需要高可靠性的智能无人机系统开发者。
大型语言模型（LLMs）的进展已推动移动机器人（包括无人机）在物联网（IoT）生态中的智能化操作。然而，当前LLMs在逻辑推理与复杂决策方面仍存在不足，导致其在物联网应用中驱动无人机操作的可靠性令人担忧。本文提出一种基于语义观测的闭环大模型驱动无人机操作代码生成框架，通过两个LLM模块——代码生成器与评估器——实现有效反馈与迭代优化。该框架将无人机运行的数值状态观测转化为语义轨迹描述，增强评估模型对无人机动态的理解，从而生成精准反馈。同时，框架引入基于仿真的优化流程，避免因错误代码执行对物理无人机造成风险。在不同复杂度的无人机控制任务上进行了大量实验。结果表明，该框架能显著提升任务成功率与完成度，尤其在任务复杂性增加时，性能远超基线方法。
原文摘要 · Abstract (English)
Recent advances in large Language Models (LLMs) have revolutionized mobile robots, including unmanned aerial vehicles (UAVs), enabling their intelligent operation within Internet of Things (IoT) ecosystems. However, LLMs still face challenges from logical reasoning and complex decision-making, leading to concerns about the reliability of LLM-driven UAV operations in IoT applications. In this paper, we propose a closed-loop LLM-driven UAV operation code generation framework that enables reliable UAV operations powered by effective feedback and refinement using two LLM modules, i.e., a Code Generator and an Evaluator. Our framework transforms numerical state observations from UAV operations into semantic trajectory descriptions to enhance the evaluator LLM's understanding of UAV dynamics for precise feedback generation. Our framework also enables a simulation-based refinement process, and hence eliminates the risks to physical UAVs caused by incorrect code execution during the refinement. Extensive experiments on UAV control tasks with different complexities are conducted. The experimental results show that our framework can achieve reliable UAV operations using LLMs, which significantly outperforms baseline methods in terms of success rate and completeness with the increase of task complexity.
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。