Reusable launch vehicles need to face complex and diverse environments during flight. The design of rocket recovery control law based on traditional deep reinforcement learning (DRL) makes it difficult to obtain a set of network architectures that can adapt to multiple scenarios and multi-parameter uncertainties, and the performance of deep reinforcement learning algorithm depends on manual trial and error of hyperparameters. To solve this problem, this paper proposes a self-learning control method for launch vehicle recovery based on neural architecture search (NAS), which decouples deep network structure search and reinforcement learning hyperparameter optimization. First, using network architecture search technology based on a multi-objective hybrid particle swarm optimization algorithm, the proximal policy optimization algorithm of deep network architecture is automatically designed, and the search space is lightweight design in the process. Secondly, in order to further improve the landing accuracy of the launch vehicle, the Bayesian optimization (BO) method is used to automatically optimize the hyperparameters of reinforcement learning, and the control law of the landing phase in the recovery process of the launch vehicle is obtained through training. Finally, the algorithm is transplanted to the rocket intelligent learning embedded platform for comparative testing to verify its online deployment capability. The simulation results show that the proposed method can satisfy the landing accuracy of the launch vehicle recovery mission, and the control effect is basically the same as the landing accuracy of the trained rocket model under the untrained condition of model parameter deviation and wind field interference, which verifies the generalization of the proposed method.

The fault tolerant control (FTC) of hypersonic flight vehicle (HFV) with actuator fault is proposed in this paper. The fault model considered in this paper is a general model which HFV may encounter in practice. For designing the FTC, the nonlinear model of HFV is represented by T-S fuzzy models, and policy iteration (PI) strategy is utilized to solve the design problem of T-S controller for the built T-S model of HFV without actuator fault. Then, based on the normal T-S controller, an adaptive fuzzy FTC controller is proposed, in which the feedback gain matrices can improve themselves according to the special fault. The stability of the proposed adaptive fuzzy FTC is proved by Lyapunov theory, and an integral reinforcement learning (IRL)–based solving algorithm is proposed. Simulations on three different kinds of actuator faults are proposed, and the simulation results show that, under three different faults, the designed adaptive FTC can ensure the reliable flight of HFV.

A data-driven nonlinear control approach, called error dynamics-based dual heuristic dynamic programming (ED-DHP), is proposed for air vehicle attitude control. To solve the optimal tracking control problem, the augmented system is defined by the derived error dynamics and reference trajectory so that the actor neural network can learn the feedforward and feedback control terms at the same time. During the online self-learning process, the actor neural network learns the control policy by minimizing the augmented system’s value function. The input dynamics identified by the recursive least square (RLS) and output of the critic neural network are used to update the actor neural network. In addition, the total uncertainty term of the error dynamics is also identified by RLS, which can compensate for the uncertainty caused by inaccurate modeling, parameter perturbation, and so on. The outputs of ED-DHP include the rough trim surface, feedforward and feedback terms from the actor neural network, and the compensation. Based on this control scheme, the complete knowledge of system dynamics and the reference trajectory dynamics are not needed, and offline learning is unnecessary. To verify the self-learning ability of ED-DHP, two numerical experiments are carried out based on the established morphing air vehicle model. One is sinusoidal signal tracking at a fixed operating point, and the other is guidance command tracking with a morphing process at variable operating points. The simulation results demonstrate the good performance of ED-DHP for online self-learning attitude control and validate the robustness of the proposed scheme

This paper is concerned with the robust fault-tolerant tracking control problem for networked control system (NCS). Firstly, considering the locally overlapped switching law widely existed in engineering applications, the NCS is modeled as a locally overlapped switched polytopic system to reduce designing conservatism and solving complexity. Then, switched parameter dependent fault-tolerant tracking controllers are constructed to deal with the asynchronous switching phenomenon caused by the updating delays of the switching signals and weighted coefficients. Additionally, the global uniform asymptotic stability in the mean (GUAS-M) and desired weightedl2performance are guaranteed by combining the switched parameter dependent Lyapunov functional method with the average dwell time (ADT) method, and the feasible conditions for the fault-tolerant tracking controllers are obtained in the form of linear matrix inequalities (LMIs). Finally, the performance of the proposed approach is verified on a highly maneuverable technology (HiMAT) vehicle’s tracking control problem. Simulation results show the effectiveness of the proposed method.