Multi-UAV-Borne Surveillance Radar Trajectory Planning Method Based on Imitation Learning

To address the high computational complexity and insufficient real-time performance of traditional multi-radar trajectory planning methods in complex multi-platform sensing scenarios, this study proposes an imitation-learning-based trajectory planning method for multi-radar systems. The method features a trajectory policy neural network architecture based on multi-semantic information, and involves a training-data construction method with coverage rate as the optimization objective. The trajectory policy neural network is then trained via an imitation-learning algorithm with an auxiliary target. Simulation results show that the proposed method achieves an average coverage rate of 93.95%, and improves the single-step decision efficiency by a factor of 6.7 compared with heuristic-based trajectory optimization methods.