SkySim: 大規模言語モデルによるドローン群の自然言語制御のためのROS2ベースシミュレーション環境
SkySim: A ROS2-based Simulation Environment for Natural Language Control of Drone Swarms using Large Language Models
LLMによる高レベル計画と人工ポテンシャル場による安全フィルタを分離し、自然言語でドローン群を安全に制御できるROS2/Gazeboシミュレータを提案・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: Aditya Shibu, Marah Saleh, Mohamed Al-Musleh, Nidhal Abdulaziz
分類: cs.RO, cs.HC
原文アブストラクト
Unmanned Aerial Vehicle (UAV) swarms offer versatile applications in logistics, agriculture, and surveillance, yet controlling them requires expert knowledge for safety and feasibility. Traditional static methods limit adaptability, while Large Language Models (LLMs) enable natural language control but generate unsafe trajectories due to lacking physical grounding. This paper introduces SkySim, a ROS2-based simulation framework in Gazebo that decouples LLM high-level planning from low-level safety enforcement. Using Gemini 3.5 Pro, SkySim translates user commands (e.g., "Form a circle") into spatial waypoints, informed by real-time drone states. An Artificial Potential Field (APF) safety filter applies minimal adjustments for collision avoidance, kinematic limits, and geo-fencing, ensuring feasible execution at 20 Hz. Experiments with swarms of 3, 10, and 30 Crazyflie drones validate spatial reasoning accuracy (100% across tested geometric primitives), real-time collision prevention, and scalability. SkySim empowers non-experts to iteratively refine behaviors, bridging AI cognition with robotic safety for dynamic environments. Future work targets hardware integration.
