AeroGen: 単発構造化プロンプトとドローンSDKによるエージェント型ドローン自律制御
AeroGen: Agentic Drone Autonomy through Single-Shot Structured Prompting & Drone SDK
LLMが生成するドローン制御コードの信頼性を高めるため、API仕様や飛行制約をプロンプトに組み込むフレームワークAeroGenを提案し、20種類のナビゲーションタスクと5つのミッションで有効性を検証した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Kautuk Astu, Yogesh Simmhan
分類: cs.RO, cs.DC
原文アブストラクト
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.
