Reinforcement learning-based anti-jamming in networked uav radar systems

Abstract

The networked unmanned aerial vehicle (UAV) radar system may exploit inter-UAV cooperation for enhancing information acquisition capabilities, meanwhile its inter-UAV communications may be interfered with by external jammers. This paper is devoted to quantifying and optimizing the anti-jamming performance of networked UAV radar systems in adversarial electromagnetic environments. Firstly, instead of using the conventional metric of signal-tointerference ratio (SIR), this paper explores use of the theory of radar information representation as the basis of evaluating the information acquisition capabilities of the networked UAV radar systems. Secondly, this paper proposes a modified Q-Learning method based on double greedy algorithm to optimize the anti-jamming performance of the networked UAV radar systems, through joint programming in the frequency-motion-antenna domain. Simulation results prove the effectiveness of the algorithm in two different networking scenarios.