The perch maneuver of an aircraft requires high-angle-of-attack flight, rapid deceleration, and precise landing in a target area, involving complex nonlinear dynamics and fast time-varying characteristics. To address the challenges posed by these dynamic complexities and stringent control performance demands, this paper proposes a trajectory control design method based on reachability sets and iterative learning. First, an improved backward reachability set computation algorithm is developed for the perch maneuver control system. Then, an iterative learning trajectory control method is introduced, guided by the reachability set to ensure convergence. This method begins with an inaccurate initial perch trajectory, and iteratively refines the trajectory and optimizes controller parameters using the reachability set of each iteration to guide the next. After several learning iterations, the aircraft can successfully perform the perch maneuver while meeting multiple constraints and accurately landing in the target area, with a large convergence domain guaranteed. Additionally, for cases where the perch maneuver model is unknown, a trajectory control method based on the SINDy identification algorithm is designed. Finally, simulation validation and comparison of the proposed reachability set algorithm and iterative learning trajectory control method are conducted. The results demonstrate that the improved reachability set algorithm more accurately captures the reachability set of the nonlinear perch model, and the designed trajectory control method can quickly learn and achieve successful perch maneuvers even with large initial deviations.

This paper presented an intelligent deformation control method based on the long short-term memory (LSTM) deep deterministic policy gradient (DDPG) algorithm, addressing the active deformation control challenges in variable configuration aircraft. A four-wing variable sweep aircraft with a tandem-wing configuration was studied, and its geometric model and aerodynamic parameters were calculated through OPENVSP, which was then used to establish the aircraft’s dynamics model. The LSTM-DDPG algorithm learning framework was designed for the accelerated climb process of the four-wing variable sweep aircraft. Under symmetrical deformation conditions, active deformation decision training was performed for longitudinal trajectory tracking. Simulation results show that the LSTM-DDPG algorithm applied to the active deformation control process converges quickly and achieves higher average rewards. Moreover, the trained active deformation controller exhibits good control performance in the trajectory tracking tasks of the four-wing variable sweep aircraft.

Considering the strong nonlinearity of Unmanned Aerial Vehicles (UAVs) resulting from high Angle of Attack (AOA) and fast maneuvering, we present a multi-model predictive control strategy for UAV maneuvering, which has a small amount of online calculation. Firstly, we divide the maneuver envelope of UAV into several sub-regions on the basis of the gap metric theory. A novel algorithm is then developed to determine the ploytopic model for each sub-region. According to this, a Robust Model Predictive Control based on the Idea of Comprehensive optimization (ICE-RMPC) is proposed. The control law is designed offline and optimized online to reduce the computational expense. Then, the ICE-RMPC method is applied to design the controllers of sub-regions. In addition, to guarantee the stability of whole closed-loop system, a multi-model switching control strategy based on guardian maps is put forward. Finally, the tracking performance of proposed control strategy is demonstrated by an illustrative example.