AeroGen：通过单次结构提示与无人机SDK实现代理无人机自主性
AeroGen: Agentic Drone Autonomy through Single-Shot Structured Prompting & Drone SDK
AI总结：
本文提出AeroGen框架，通过结构化提示和AeroDaaS SDK实现无人机自主控制程序的可靠生成，验证了其在多种环境下的有效性。
AI中文摘要：
设计正确的无人机自主程序具有挑战性，因为需要联合导航、感知和分析需求。尽管LLM可以生成代码，但其在安全关键型无人机中的可靠性仍存疑。本文提出了AeroGen，一个开环框架，通过结构化护栏提示和与AeroDaaS无人机SDK的集成，使LLM能够通过单次生成产生一致正确的无人机控制程序。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LLM能够从用户提示中生成具有约束条件的代码，且仅需少量示例代码。我们评估了AeroGen在20个导航任务和5个无人机任务上的表现，涵盖城市、农场和检查环境，并使用命令式和声明式用户提示。AeroGen在每个任务中约生成40行AeroDaaS Python代码，耗时约20秒，无论是现实世界还是模拟环境，均显示结构化提示与明确SDK的结合提高了LLM生成无人机自主程序的鲁棒性、正确性和可部署性。
英文摘要：
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.
