让非专家用自然语言控制无人机群，安全高效。
SkySim: A ROS2-based Simulation Environment for Natural Language Control of Drone Swarms using Large Language Models
- 用大模型理解指令生成路径，再用物理规则实时修正
- 30架无人机同时飞行，100%准确实现圆形等几何形状
- 适合想快速测试无人机编队的科研或应用人员
无人机集群在物流、农业和监控中应用广泛，但传统控制需专业知识且难以适应变化。大型语言模型（LLMs）虽能理解自然语言指令，但生成的轨迹缺乏物理约束，存在安全隐患。本文提出基于ROS2与Gazebo的SkySim仿真环境，将大模型高层规划与低层安全控制解耦。采用Gemini 3.5 Pro将用户指令（如“形成圆圈”）转化为空间航点，并结合实时无人机状态进行调整。通过人工势场（APF）安全滤波器，在20 Hz频率下对轨迹做最小化修正，确保避障、满足运动学限制及地理围栏要求。在3、10、30架Crazyflie无人机的实验中，验证了空间推理准确率100%、实时防碰撞能力与良好可扩展性。该系统使非专家可迭代优化行为，实现人工智能认知与机器人安全的融合，未来将推进硬件集成。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。