Task allocation is a key aspect of Unmanned Aerial Vehicle (UAV) swarm collaborative operations. With an continuous increase of UAVs’ scale and the complexity and uncertainty of tasks, existing methods have poor performance in computing efficiency, robustness, and real-time allocation, and there is a lack of theoretical analysis on the convergence and optimality of the solution. This paper presents a novel intelligent framework for distributed decision-making based on the evolutionary game theory to address task allocation for a UAV swarm system in uncertain scenarios. A task allocation model is designed with the local utility of an individual and the global utility of the system. Then, the paper analytically derives a potential function in the networked evolutionary potential game and proves that the optimal solution of the task allocation problem is a pure strategy Nash equilibrium of a finite strategy game. Additionally, a PayOff-based Time-Variant Log-linear Learning Algorithm (POTVLLA) is proposed, which includes a novel learning strategy based on payoffs for an individual and a time-dependent Boltzmann parameter. The former aims to reduce the system’s computational burden and enhance the individual’s effectiveness, while the latter can ensure that the POTVLLA converges to the optimal Nash equilibrium with a probability of one. Numerical simulation results show that the approach is optimal, robust, scalable, and fast adaptable to environmental changes, even in some realistic situations where some UAVs or tasks are likely to be lost and increased, further validating the effectiveness and superiority of the proposed framework and algorithm.

The direct lift control method of automatic landing based on Proximal Policy Optimization (PPO) algorithm was proposed to solve the problem that it is easy to touch ship due to disturbance of deck movement and carrier air wake during automatic landing of carrier aircraft. The PPO controller takes six state variables of pitch angle, height, flight path angle, pitch angle rate, height error and flight path angle rate as input and output as flap deflection angle, realizing the rapid response of carrier aircraft in different landing states of flight path angle. Compared with traditional PID controller, the Actor-Critic network in PPO controller greatly improves the calculation efficiency of control quantity, and also reduces the difficulty of parameter optimization. The simulation experiment in this paper is based on the dynamics/kinematics model of F/A-18 aircraft constructed in Matlab/Simulink. The intensive learning and training environment built on PyCharm platform is used to realize the data interaction between the two platforms through user datagram protocol (UDP) communication. The simulation results show that the proposed method has the characteristics of fast response speed and small dynamic error, and can stabilize the landing height error within ±0.2 m, with high control accuracy.