To solve the problems of autonomous decision making and the cooperative operation of multiple unmanned combat aerial vehicles (UCAVs) in beyond-visual-range air combat, this paper proposes an air combat decision-making method that is based on a multi-agent proximal policy optimization (MAPPO) algorithm. Firstly, the model of the unmanned combat aircraft is established on the simulation platform, and the corresponding maneuver library is designed. In order to simulate the real beyond-visual-range air combat, the missile attack area model is established, and the probability of damage occurring is given according to both the enemy and us. Secondly, to overcome the sparse return problem of traditional reinforcement learning, according to the angle, speed, altitude, distance of the unmanned combat aircraft, and the damage of the missile attack area, this paper designs a comprehensive reward function. Finally, the idea of centralized training and distributed implementation is adopted to improve the decision-making ability of the unmanned combat aircraft and improve the training efficiency of the algorithm. The simulation results show that this algorithm can carry out a multi-aircraft air combat confrontation drill, form new tactical decisions in the drill process, and provide new ideas for multi-UCAV air combat.

Multi-UAV cooperative path planning can improve the efficiency of task completion. To deal with the space and time conflicts of multi-UAVs in complex environments, a multi-collision-based multi-UAV cooperative path planning algorithm, multi-conflict-based search (MCBS), is proposed. First, the flight and cooperative constraints of UAV are analyzed, and a three-dimensional environment model is established that incorporates geographical information. Then, hierarchical optimization is used to design collaborative algorithms. In the low-level path design, UAV flight constraints are combined with a sparse A* algorithm, and by improving the cost function, the search space is reduced, and the search time is shortened. In high-level cooperation, the priorities of different conflicts are set, heuristic information is introduced to guide the constraint tree to grow in the direction of satisfying the constraints, and the optimal path set is searched by the best priority search algorithm to reduce the convergence time. Finally, the planning results of the proposed algorithm, the traditional CBS algorithm, and the sparse A* algorithm for different UAV tasks are compared, and the influence of the optimization parameters on the calculation results is discussed. The simulation results show that the proposed algorithm can solve cooperative conflict between UAVs, improve the efficiency of path searches, and quickly find the optimal safe cooperative path that satisfies flight and cooperative constraints.