用结构化提示+无人机SDK，让大模型一键生成安全可靠的航拍程序。
AeroGen: Agentic Drone Autonomy through Single-Shot Structured Prompting & Drone SDK
- 通过结构化提示将飞行规则和API直接注入上下文，让大模型自动生成合规代码。
- 在20个导航任务和5个真实场景任务中，平均20秒生成约40行可运行代码。
- 适合需要快速部署无人机自主程序的开发者，尤其适合非专业程序员使用。
设计正确的无人机自主程序面临导航、感知与分析协同的挑战。尽管大语言模型（LLM）能生成代码，但其在安全关键型无人机上的可靠性仍存疑。本文提出AeroGen，一个开环框架，通过结构化约束提示与AeroDaaS无人机SDK集成，实现单次生成即正确的目标。AeroGen将API说明、飞行约束及环境规则编码至系统提示上下文，使通用大模型仅凭用户指令即可生成符合约束的代码，且无需大量示例。我们在包含20个导航任务和5个真实场景任务（城市、农田、巡检）的多样化基准上进行评估，使用命令式与声明式用户指令。AeroGen平均每项任务20秒内生成约40行AeroDaaS Python代码，无论在真实环境还是仿真中均表现稳定，证明结合明确的SDK与结构化提示能显著提升生成代码的鲁棒性、正确性和可部署性。
原文摘要 · Abstract (English)
Designing correct UAV autonomy programs is challenging due to joint navigation, sensing and analytics requirements. While LLMs can generate code, their reliability for safety-critical UAVs remains uncertain. This paper presents AeroGen, an open-loop framework that enables consistently correct single-shot AI-generated drone control programs through structured guardrail prompting and integration with the AeroDaaS drone SDK. AeroGen encodes API descriptions, flight constraints and operational world rules directly into the system context prompt, enabling generic LLMs to produce constraint-aware code from user prompts, with minimal example code. We evaluate AeroGen across a diverse benchmark of 20 navigation tasks and 5 drone missions on urban, farm and inspection environments, using both imperative and declarative user prompts. AeroGen generates about 40 lines of AeroDaaS Python code in about 20s per mission, in both real-world and simulations, showing that structured prompting with a well-defined SDK improves robustness, correctness and deployability of LLM-generated drone autonomy programs.
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。