基于强化学习的装甲救护车火线伤员收拢前接策略

Study on Strategy of Picking up the Wounded of Armoured Ambulances in Battle Line Based on Reinforcement Learning

针对进攻战斗火线伤员收拢前接时效救治需要,综合考虑战场装甲救护车数量、营救护站到火线伤员集伤点距离、不同伤势伤员人数等复杂环境条件,以伤员平均等待救治时间最短为优化目标,建立基于强化学习的装甲救护车火线伤员收拢前接策略模型,并进行优化求解计算。实验结果表明,将强化学习应用于装甲救护车火线伤员收拢前接中,有助于提升火线伤员救治效率。

In order to meet the demand of time-effect treatment of picking up the wounded in battle line,considering the number of the armored ambulances,the distance between the battalion first-aid station and the place where the wounded are concentrated,the number of the wounded with different injuries,and other complex environmental conditions,the optimization objective is the shortest average waiting time for treatment and cure.Strategy model of picking up the wounded of armored ambulances based on reinforcement learning is established to make optimization and calculation.The experiment results show that the application of reinforcement learning in picking up the wounded of armored ambulances in battle line is helpful to improve the treatment and cure efficiency of the wounded.