Adversarial Strategy for Swarm UAVs Gaming with Real-Time Interaction

The Unmanned Aerial Vehicle (UAV) swarm confrontation problem has become a hot research topic in the field of intelligent control systems in recent years, possessing significant value in artificial intelligence and environmental monitoring and protection. To address the issue of unstable striking ability in battlefield environments, leading to combat inefficiency, we propose a multi-objective optimization game-theoretic confrontation method. This method establishes a dynamic game model based on pure strategy gains with the target. We develop a real-time interactive Laplace matrix to enhance synergy between our UAV swarms. Additionally, a topological method is employed to achieve stable control by designing a real-time mutual interaction synergy structure based on mission state. Finally, the efficient encoding and decoding capabilities of the Transformer model, combined with the multi-intelligence deep deterministic policy gradient algorithm, improve the model's ability to handle state space representations while enabling the UAV swarm to better understand the complex interactions between intelligences. Simulations are conducted using an adversarial decision-making algorithm based on game theory and cooperative communication structures in 2v2 simple scenarios and 4v4 complex scenarios. Compared with the benchmark algorithm, the algorithm in this paper converges faster, is more robust, and takes less time to win the confrontation.