عنوان انگلیسی مقاله:
Reinforcement learning based two-level control framework of UAV swarm for cooperative persistent surveillance in an unknown urban area
ترجمه فارسی عنوان مقاله:
چارچوب کنترل دو سطح مبتنی بر یادگیری تقویتی برای پایش مداوم همکاری در یک منطقه ناشناخته شهری
Sciencedirect - Elsevier - Aerospace Science and Technology, 98 (2020) 105671: 10:1016/j:ast:2019:105671
YuxuanLiu, HuLiu, YongliangTian∗, CongSun
Persistent surveillance in a complex unknown urban area by an unmanned aerial vehicle (UAV) swarm is a low-cost, promising future application for anti-terrorism, disaster monitoring, and battlefield situational awareness. Based on over-simplified simulated surroundings and a UAV dynamic model, a few remarkable approaches have been proposed; however, they typically rely on non-sensor-based inputs and prior knowledge on the environment or targets. To overcome these limitations, based on simulated city blocks, a two-level quasi-distributed control framework is proposed for realizing the continuous control of a UAV swarm in two defined surveillance phases. With the support of a well-trained and corrected artificial neural network (ANN) in low-level UAV manoeuvre control for target homing and collision avoidance, several preliminary high-level target allocation strategies are designed for a cooperative overall objective based on the synchronization of local surveillance data. Then, via a series of numerical simulations, an optimal high-level strategy combination is identified. Finally, the surveillance performance of this strategy combination is evaluated under various swarm sizes and UAV launching patterns. The simulation results demonstrate that the proposed control framework is applicable for UAV swarm control in the persistent surveillance of unknown urban areas.
Keywords: UAV swarm | Reinforcement learning | Persistent surveillance | Autonomous manoeuvre control | Artificial neural network (ANN)