Online waveform selection for cognitive radar
This addresses the domain-specific challenge of missile tracking for radar systems, representing an incremental improvement through the application of reinforcement learning to waveform parameter selection.
The paper tackled the problem of tracking ballistic missiles by developing adaptive waveform selection algorithms for cognitive radar systems, demonstrating through experiments on synthetic trajectories that their reinforcement learning approaches successfully minimized range error while maintaining continuous target tracking.
Designing a cognitive radar system capable of adapting its parameters is challenging, particularly when tasked with tracking a ballistic missile throughout its entire flight. In this work, we focus on proposing adaptive algorithms that select waveform parameters in an online fashion. Our novelty lies in formulating the learning problem using domain knowledge derived from the characteristics of ballistic trajectories. We propose three reinforcement learning algorithms: bandwidth scaling, Q-learning, and Q-learning lookahead. These algorithms dynamically choose the bandwidth for each transmission based on received feedback. Through experiments on synthetically generated ballistic trajectories, we demonstrate that our proposed algorithms achieve the dual objectives of minimizing range error and maintaining continuous tracking without losing the target.