AeroGen: Agentic Drone Autonomy through Single-Shot Structured Prompting & Drone SDK
This addresses the problem of safety-critical UAV autonomy for developers by improving reliability through incremental enhancements in prompting and SDK integration.
The paper tackles the challenge of generating reliable drone autonomy programs by introducing AeroGen, a framework that uses structured prompting with a drone SDK to produce correct code from user prompts, achieving robust results across 20 navigation tasks and 5 missions with about 40 lines of code generated in 20 seconds per mission.
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.