In this work, aiming at the problem of cooperative task assignment for multiple unmanned aerial vehicles (UAVs) in actual combat, battlefield tasks are divided into reconnaissance tasks, strike tasks and evaluation tasks, and a cooperative task-assignment model for multiple UAVs is built. Meanwhile, heterogeneous UAV-load constraints and mission-cost constraints are introduced, the UAVs and their constraints are analyzed and the mathematical model is established. The exploration performance and convergence performance of the harmony search algorithm are analyzed theoretically, and the more general formulas of exploration performance and convergence performance are proved. Based on theoretical analysis, an algorithm called opposition-based learning parameter-adjusting harmony search is proposed. Using the algorithm to test the functions of different properties, the value range of key control parameters of the algorithm is given. Finally, four algorithms are used to simulate and solve the assignment problem, which verifies the effectiveness of the task-assignment model and the excellence of the designed algorithm. Simulation results show that while ensuring proper assignment, the proposed algorithm is very effective for the multi-objective optimization of heterogeneous UAV-cooperation mission planning with multiple constraints.

Autonomous maneuver decision by an unmanned combat air vehicle (UCAV) is a critical part of air combat that requires both flight safety and tactical maneuvering. In this paper, an unmanned combat air vehicle air combat maneuver decision method based on a proximal policy optimization algorithm (PPO) is proposed. Firstly, a motion model of the unmanned combat air vehicle and a situation assessment model of air combat was established to describe the motion situation of the unmanned combat air vehicle. An enemy maneuver policy based on a situation assessment with a greedy algorithm was also proposed for air combat confrontation, which aimed to verify the performance of the proximal policy optimization algorithm. Then, an action space based on a basic maneuver library and a state observation space of the proximal policy optimization algorithm were constructed, and a reward function with situation reward shaping was designed for accelerating the convergence rate. Finally, a simulation of air combat confrontation was carried out, which showed that the agent using the proximal policy optimization algorithm learned to combine a series of basic maneuvers, such as diving, climb and circling, into tactical maneuvers and eventually defeated the enemy. The winning rate of the proximal policy optimization algorithm reached 62%, and the corresponding losing rate was only 11%.

To tackle challenges such as convergence difficulties and suboptimal performance in the application of reinforcement learning to intelligent decision-making for joint operations, this study introduces an enhanced decision-making approach for joint operations utilizing an improved Proximal Policy Optimization (PPO) algorithm. We propose a structured intelligent decision-making model designed to execute decision-making functions effectively. The strategy loss mechanism is improved by constraining the upper limit of the strategy loss function. Furthermore, a priority sampling mechanism, is developed to assess sample values, thereby enhancing the efficiency of sampling training. Additionally, a network structure facilitating distributed interaction and centralized learning is designed to expedite the training process. The proposed method is then applied to a joint operations simulation platform for intelligent decision-making. Simulation results demonstrate that our algorithm successfully addresses the aforementioned issues, enabling autonomous decisions based on battlefield dynamics, and ultimately leading to victory.