An adaptive proportional navigation law with intelligent parameter adjustment by deep reinforcement learning is presented to address the issue of excessive miss distances and energy loss in the interception of moving targets using fixed coefficient proportional navigation law. First, a state space based on real-time flight states, an action space containing lateral and vertical gains, and a reward function model integrating different states is established. Meanwhile, a prediction-correction method is introduced to improve the accuracy of action evaluation in the model design of the reward function. Secondly, the soft actor-critic (SAC) algorithm is employed to train a network parameter and guidance parameter decision system that takes into account the miss distances and energy loss according to the relative motion states of the interceptor and the target. In comparison to traditional proportional navigation guidance, the simulation results demonstrate that the guidance technique has strong adaptability and can greatly minimize energy loss while retaining low miss distances.

In order to solve the distributed cooperative guidance problem in the flight process of a high-velocity aircraft swarm, this paper proposed an adaptive topology optimization and guidance algorithm based on a minimum spanning tree. The algorithm constructed the topology graph of the communication link of the aircraft swarm, quantified the distance as the weight according to the communication cost, and generated the optimal communication topology graph in real time through the idea of the Kruskal algorithm in the minimum spanning tree. This paper adopted the distributed two-layer cooperative guidance framework and multi-center distributed topology optimization decision-making method and compensated for the consistent variables in the consensus cooperative control law, so as to realize the topology adaptive optimization and control in the cooperative flight of aircraft swarm. Simulation results verify the effectiveness and excellent performance of the proposed algorithm.