用深度强化学习让无人机在复杂城市气流中自主导航
Navigation in a Three-Dimensional Urban Flow using Deep Reinforcement Learning
- 结合流场感知的PPO算法与GTrXL模型，提升对湍流环境的理解
- 成功率达92%，撞毁率低于3%，显著优于传统方法
- 适合研究无人机自主飞行、智能交通系统的开发者
无人飞行器（UAV）在城市环境中日益广泛用于配送与监视。本文基于深度强化学习，构建了一种面向三维高保真城市流场（含湍流与回流区）的最优导航策略。所提算法采用流场感知的近端策略优化（PPO）结合门控变压器扩展大模型（GTrXL），使智能体能更充分获取复杂湍流场信息。实验对比了无辅助预测任务的PPO+GTrXL、PPO+LSTM及传统Zermelo导航算法。结果表明，该方法成功率（SR）达92%，撞毁率（CR）低于3%，显著优于其他基线方法，为复杂城市环境下无人机自主导航提供了全新范式。
原文摘要 · Abstract (English)
Unmanned Aerial Vehicles (UAVs) are increasingly populating urban areas for delivery and surveillance purposes. In this work, we develop an optimal navigation strategy based on Deep Reinforcement Learning. The environment is represented by a three-dimensional high-fidelity simulation of an urban flow, characterized by turbulence and recirculation zones. The algorithm presented here is a flow-aware Proximal Policy Optimization (PPO) combined with a Gated Transformer eXtra Large (GTrXL) architecture, giving the agent richer information about the turbulent flow field in which it navigates. The results are compared with a PPO+GTrXL without the secondary prediction tasks, a PPO combined with Long Short Term Memory (LSTM) cells and a traditional navigation algorithm. The obtained results show a significant increase in the success rate (SR) and a lower crash rate (CR) compared to a PPO+LSTM, PPO+GTrXL and the classical Zermelo's navigation algorithm, paving the way to a completely reimagined UAV landscape in complex urban environments.
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。