用强化学习让无人机自主点对点飞行，无需人工干预。
Reinforcement Learning for Autonomous Point-to-Point UAV Navigation
- 通过试错学习构建导航策略，奖励机制鼓励高效抵达
- 实机测试中实现低人为干预的稳定点对点飞行
- 适合需要自主飞行的巡检、配送场景
无人机在自动化巡检、配送和导航任务中日益重要，亟需可靠自主能力。本项目开发了一种基于强化学习（RL）的方法，使单架无人机能自主从预设点位间导航，无需人工干预。无人机通过与环境的试错交互学习导航策略，采用自定义奖励函数，鼓励高效到达目标，同时惩罚碰撞和不安全行为。控制系统结合ROS与Gym兼容训练环境，支持灵活部署与测试。训练完成后，将学习到的策略部署于真实无人机平台，在实际条件下进行评估。结果表明，该系统可在极少人工监督下完成自主导航，验证了基于强化学习的控制在现实场景中点对点无人机操作的可行性。
原文摘要 · Abstract (English)
Unmanned Aerial Vehicles (UAVs) are increasingly used in automated inspection, delivery, and navigation tasks that require reliable autonomy. This project develops a reinforcement learning (RL) approach to enable a single UAV to autonomously navigate between predefined points without manual intervention. The drone learns navigation policies through trial-and-error interaction, using a custom reward function that encourages goal-reaching efficiency while penalizing collisions and unsafe behavior. The control system integrates ROS with a Gym-compatible training environment, enabling flexible deployment and testing. After training, the learned policy is deployed on a real UAV platform and evaluated under practical conditions. Results show that the UAV can successfully perform autonomous navigation with minimal human oversight, demonstrating the viability of RL-based control for point-to-point drone operations in real-world scenarios.
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。