Aiming at the attitude control of a class of hypersonic morphing vehicles (HMVs) with variable sweep wings, a model-free adaptive dynamic planning (MFADP) optimal control method based on data-driven and finite-time fuzzy disturbance observer is proposed in this paper. An integrated oriented-control attitude-morphing model is established, and morphing is considered as the state to carry out the integrated coupling attitude control. The control scheme is organized by a steady-feedback-compensation framework. To overcome the dependence on the unknown dynamic knowledge of HMVs, the dynamic model is reconstructed using neural networks for steady-state control. Subsequently, based on the MFADP algorithm, an Off-On serial policy learning strategy is designed for the error model to obtain a real-time approximate optimal feedback control. Additionally, a fuzzy disturbance observer with finite-time convergence ability is proposed to estimate and compensate the multiple uncertainties. Finally, the stability of the closed-loop system is proved theoretically and the simulation results demonstrate the improved performance of the proposed method.

The morphing aircraft can improve the flight performance of hypersonic vehicles by satisfying the flight requirements of large airspace and large velocity field. In this paper, for the hypersonic variable span missile, the dynamic model and aerodynamic model are established on the variable span characteristic. The adaptive dynamic surface control back-stepping method is used to establish the integrated guidance and control (IGC) with terminal angular constraint in the dive phase of the hypersonic variable span missile. The span variety is used to assist the lift control to achieve fast and stable control for the centroid motion. The simulation results demonstrate that the feasibility and robustness of the IGC method of the hypersonic variable span missile is better than the invariable span.

An onboard three-dimensional (3D) trajectory generation approach based on the reinforcement learning (RL) algorithm and deep neural network (DNN) is proposed for hypersonic vehicles in glide phase. Multiple trajectory samples are generated offline through the convex optimisation method. The deep learning (DL) is employed to pre-train the DNN for initialising the actor network and accelerating the RL process. Based on the offline deep policy deterministic actor-critic algorithm, a flight target-oriented reward function with path constraints is designed. The actor network is optimised by the end-to-end RL and policy gradients of the critic network until the reward function converges to the maximum. The actor network is considered as the onboard trajectory generator to compute optimal control values online based on the real-time motion states. The simulation results show that the single-step online planning time meets the real-time requirements of onboard trajectory generation. The significant improvement in terminal accuracy of the online trajectory and the better generalisation under biased initial states for hypersonic vehicles in glide phase is observed.

An autonomous optimal trajectory planning method based on the deep deterministic policy gradient (DDPG) algorithm of reinforcement learning (RL) for hypersonic vehicles (HV) is proposed in this paper. First, the trajectory planning problem is converted into a Markov Decision Process (MDP), and the amplitude of the bank angle is designated as the control input. The reward function of the MDP is set to minimize the trajectory terminal position errors with satisfying hard constraints. The deep neural network (DNN) is used to approximate the policy function and action-value function in the DDPG framework. The Actor network then computes the control input directly according to flight states. Using a limited exploration strategy, the optimal policy network would be considered fully trained when the reward value reached maximum convergence. Simulation results show that the policy network trained using a DDPG algorithm accomplishes 3-dimensional (3D) trajectory planning during the HV glide phase with high terminal precision and stable convergence. Additionally, the single step calculation time of the policy network occurs in near real time, which suggests great potential as an autonomous online trajectory planner. Monte Carlo experiments prove the strong robustness of the implementation of an autonomous trajectory planner under aerodynamic disturbances.