Unmanned Aerial Vehicle Defense Penetration on a Digital-Twin-City Based on an Improved MASAC Reinforcement Learning

In this paper, we investigate the use of multi-UAVs (Unmanned Aerial Vehicles) for defense penetration in an urban environment with obstacles. To ensure a high-quality scenario of the urban environment, a digital-twin-city simulation platform is proposed featuring a powerful physics engine and real-time interaction technology. Subsequently, an improved multi-agent soft actor-critic (MASAC) method with a target prediction network is introduced to enhance the effectiveness of the cooperative multi-UAV system in defense penetration missions. Finally, the performance of the proposed improved MASAC method is evaluated through comparative experiments.