DNN-Based H∞ Decentralized Attack-Tolerant Team Formation Tracking Design of Large-Scale UAV Networked Control System under Time-Varying Delay and Interconnected Coupling
Bor‐Sen Chen · 2024
In this chapter, a robust decentralized H ∞ attack-tolerant observer-based team formation tracking control scheme is proposed for large-scale quadrotor UAV systems under external disturbance, measurement noise, couplings from other neighboring quadrotor UAVs, and malicious attacks on actuator and sensor of NCS via wireless communication. By integrating the smoothed model of attack signals with the system state of each quadrotor UAV, we can simultaneously estimate the attack signals and the system state of each quadrotor UAV for the efficient robust decentralized H ∞ attack-tolerant observer-based team formation tracking control of large-scale quadrotor UAVs. The design of robust decentralized H ∞ attack-tolerant observer-based team formation tracking control of large-scale quadrotor UAVs needs to solve a very difficult independent nonlinear partial differential observer/controller-coupled Hamilton Jacobi Issac equation (HJIE) for the observer and controller design of each quadrotor UAV. Nowadays, there are no analytical and numerical methods to resolve HJIE. Thus, an HJIE-reinforcement-based deep neural network (DNN) is trained by Adam learning algorithm to directly solve the observer/controller-coupled HJIE for robust decentralized H ∞ attack-tolerant observer-based team formation tracking control of each quadrotor UAV. As the Adam algorithm converges, we could show that the proposed HJIE-reinforcement DNN-based decentralized H ∞ attack-tolerant observer-based tracking control strategy can be achieved.