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.

翻译：由于需要同时满足导航、感知与分析的要求，设计正确的无人机自主控制程序具有挑战性。虽然大语言模型能够生成代码，但其在安全关键型无人机应用中的可靠性仍不确定。本文提出AeroGen，一种开环框架，通过结构化护栏提示以及与AeroDaaS无人机SDK的集成，能够持续生成正确的单次AI驱动无人机控制程序。AeroGen将API描述、飞行约束和操作世界规则直接编码到系统上下文提示中，使通用大语言模型能够根据用户提示生成具备约束感知的代码，且仅需极少量示例代码。我们在城市、农场和巡检环境中的20项导航任务和5项无人机任务构成的多样化基准测试上评估AeroGen，同时使用命令式和声明式用户提示。AeroGen在现实世界和仿真环境中，每项任务约20秒生成约40行AeroDaaS Python代码，结果表明：结合明确定义的SDK进行结构化提示，能够提升大语言模型生成的无人机自主控制程序的鲁棒性、正确性和可部署性。