Autonomous air combat decision-making of UAV based on parallel self-play reinforcement learning

Aiming at addressing the problem of manoeuvring decision-making in UAV air combat,this study establishes a one-to-one air combat model,defines missile attack areas,and uses the non-deterministic policy Soft-Actor-Critic(SAC)algorithm in deep reinforcement learning to construct a decision model to realize the manoeuvring process.At the same time,the complexity of the proposed algorithm is calculated,and the stability of the closed-loop system of air combat decision-making controlled by neural network is analysed by the Lyapunov function.This study defines the UAV air combat process as a gaming process and proposes a Parallel Self-Play training SAC algorithm(PSP-SAC)to improve the generalisation performance of UAV control decisions.Simulation results have shown that the proposed algorithm can realize sample sharing and policy sharing in multiple combat environments and can significantly improve the generalisation ability of the model compared to independent training.

HEURISTIC QUANTUM GENETIC ALGORITHM FOR AIR COMBAT DECISION MAKING ON COOPERATIVE MULTIPLE TARGET ATTACK

In order to achieve the optimal attack outcome in the air combat under the beyond visual range(BVR)condition,the decision-making(DM)problem which is to set a proper assignment for the friendly fighters on the hostile fighters is the most crucial task for cooperative multiple target attack(CMTA).In this paper,a heuristic quantum genetic algorithm(HQGA)is proposed to solve the DM problem.The originality of our work can be supported in the following aspects:(1)the HQGA assigns all hostile fighters to every missile rather than fighters so that the HQGA can encode chromosomes with quantum bits(Q-bits);(2)the relative successful sequence probability(RSSP)is defined,based on which the priority attack vector is constructed;(3)the HQGA can heuristically modify quantum chromosomes according to modification technique proposed in this paper;(4)last but not the least,in some special conditions,the HQGA gets rid of the constraint described by other algorithms that to obtain a better result.In the end of this paper,two examples are illustrated to show that the HQGA has its own advantage over other algorithms when dealing with the DM problem in the context of CMTA.