高速变外形飞行器双阶段智能决策的时间约束 再入制导

In order to realize the time-constrained entry for the hypersonic morphing vehicle, a time-constrained entry guidance method with double-stage intelligent decision-making framework is proposed. By combining the morphing decision-making and entry guidance, a time-constrained framework with double-stage intelligent decision-making is constructed to enlarge the time adjustment range of the hypersonic morphing vehicle. With the proposed framework, the time constraint problem is modeled as a multi-agent Markov decision problem. A flight time adjustment strategy based on multi-agent reinforcement learning is then designed to guide the hypersonic morphing vehicle to the terminal position at a specified time by adjusting its lateral motion. Furthermore, the longitudinal guidance method is designed considering the real-time state feedback in the reference change rate of the flight state. Guidance commands of the angle of attack and the bank angle is proposed in analytical form to meet the terminal velocity and time constraints. The proposed longitudinal guidance method ensures a precise terminal state control of the hypersonic morphing vehicle under different configurations with significant differences in aerodynamic characteristics. Theoretical analysis and numerical simulations demonstrate that the proposed method can improve the time adjustment ability of the hypersonic morphing vehicle during the entry process. The method exhibits high guidance precision and robustness.