用物理约束神经网络优化无人机动态环境路径，更省能更平滑。
A Physics-Informed Neural Network Approach for UAV Path Planning in Dynamic Environments
- 将无人机动力学与风扰、避障直接嵌入神经网络训练过程
- 相比A*和Kino-RRT*，控制能耗降低18%，路径更平滑且安全裕度更高
- 无需标注数据，适合复杂动态环境下的实时路径规划
在动态风场中运行的无人飞行器（UAV）必须在物理与环境约束下生成安全且节能的轨迹。传统规划方法如A*和动力学随机快速扩展树（Kino-RRT*）因离散化与采样限制，常产生次优或不光滑的路径。本文提出一种物理信息神经网络（PINN）框架，将无人机动力学、风扰与障碍物规避直接嵌入学习过程。该方法无需监督数据，通过最小化物理残差与风险感知目标，学习出动态可行且无碰撞的轨迹。对比仿真显示，所提方法在控制能耗、路径平滑性与安全裕度上均优于A*和Kino-RRT*，同时保持相当的飞行效率。结果表明，物理信息学习可统一模型驱动与数据驱动规划，为无人机轨迹优化提供可扩展且物理一致的框架。
原文摘要 · Abstract (English)
Unmanned aerial vehicles (UAVs) operating in dynamic wind fields must generate safe and energy-efficient trajectories under physical and environmental constraints. Traditional planners, such as A* and kinodynamic RRT*, often yield suboptimal or non-smooth paths due to discretization and sampling limitations. This paper presents a physics-informed neural network (PINN) framework that embeds UAV dynamics, wind disturbances, and obstacle avoidance directly into the learning process. Without requiring supervised data, the PINN learns dynamically feasible and collision-free trajectories by minimizing physical residuals and risk-aware objectives. Comparative simulations show that the proposed method outperforms A* and Kino-RRT* in control energy, smoothness, and safety margin, while maintaining similar flight efficiency. The results highlight the potential of physics-informed learning to unify model-based and data-driven planning, providing a scalable and physically consistent framework for UAV trajectory optimization.
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。