Abstract
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.
Abstract (translated)
无人飞行器(UAV)在自动化检查、交付和导航任务中越来越常用,这些任务需要可靠的自主性。本项目开发了一种强化学习(RL)方法,使单个无人机能够在预定义的点之间自主导航,并且无需人工干预。通过试错互动,无人机使用自定义奖励函数来学习导航策略,该奖励函数鼓励达到目标的有效性并惩罚碰撞和不安全行为。控制系统结合了ROS与兼容Gym的训练环境,允许灵活部署和测试。经过训练后,所学政策被部署到真实的UAV平台上,并在实际条件下进行评估。 结果显示,无人机能够在最少的人类监督下成功执行自主导航任务,这表明基于强化学习控制的方法对于现实世界中点对点无人机操作具有可行性。
URL
https://arxiv.org/abs/2509.13943