There is a growing need for uncrewed aerial vehicles (UAVs) to operate in cities. However, the uneven urban landscape and complex street systems cause large-scale wind gusts that challenge the safe and effective operation of UAVs. Current gust alleviation methods rely on traditional control surfaces and computationally expensive modeling to select a control action, leading to a slower response. Here, we used deep reinforcement learning to create an autonomous gust alleviation controller for a camber-morphing wing. This method reduced gust impact by 84%, directly from real-time, on-board pressure signals. Notably, we found that gust alleviation using signals from only three pressure taps was statistically indistinguishable from using six signals. This reduced-sensor fly-by-feel control opens the door to UAV missions in previously inoperable locations.
翻译:随着无人机(Unmanned Aerial Vehicle, UAV) 在城市中的操作需求不断增长,不平坦的城市景观和复杂的街道系统会产生大规模的风阵,对无人机的安全和有效操作提出了挑战。当前的降噪方法依赖于传统的控制表面和计算密集的模型来选择控制动作,导致响应速度较慢。在这里,我们使用深度强化学习来创建一个自主降噪控制器,应用于一种弯曲变形的机翼。该方法通过实时的、基于压力传感器的信号将降噪效果降低了84%。值得注意的是,我们发现,使用仅三个压力传感器信号的降噪效果与使用六个信号的结果在统计学上无法区分。这种降噪控制方式大大降低了传感器的数量,为先前无法操作的区域的无人机任务打开了大门。