贾永楠(通讯作者). 基于动态贝叶斯网络的多无人机集群对抗策略研究(群体智能专刊)[J]. 工程科学学报. DOI: 10.13374/j.issn2095-9389.2023.10.12.001
引用本文: 贾永楠(通讯作者). 基于动态贝叶斯网络的多无人机集群对抗策略研究(群体智能专刊)[J]. 工程科学学报. DOI: 10.13374/j.issn2095-9389.2023.10.12.001
Research on Multi-UAV Swarm Confrontation Strategy Based on Dynamic Bayesian Network[J]. Chinese Journal of Engineering. DOI: 10.13374/j.issn2095-9389.2023.10.12.001
Citation: Research on Multi-UAV Swarm Confrontation Strategy Based on Dynamic Bayesian Network[J]. Chinese Journal of Engineering. DOI: 10.13374/j.issn2095-9389.2023.10.12.001

基于动态贝叶斯网络的多无人机集群对抗策略研究(群体智能专刊)

Research on Multi-UAV Swarm Confrontation Strategy Based on Dynamic Bayesian Network

  • 摘要: 近年来,随着无人机集群攻防对抗问题在军事领域的重要性日益凸显,围绕无人机集群攻防对抗的相关研究成果不断涌现。由于该问题的基本研究框架融合了博弈论思想和分布式控制理论等复杂系统的研究热点,因而该问题也成为了众多复杂系统学者关心的热点难题。首先,本文针对红蓝双方集群攻防对抗问题,提出了一种基于改进后的兰彻斯特方程的对抗博弈模型。其次,基于该对抗模型,探讨了对抗博弈过程中的多目标任务分配问题。之后,本文在传统Kuhn-Munkres(KM)算法基础上,通过适应性改进设计出一种全新的、适用于对抗环境下的红蓝双方多无人机集群打击任务分配策略,可有效解决打击冲突难题,提高无人机集群对抗能力。再次,为了提升无人机个体的环境适应性,特别是实时、高效应对集群攻防对抗过程中产生的一系列不确定性因素,本文提出了一种集群攻防对抗策略,在对红蓝双方无人机集群对抗过程中所产生的不确定性进行预测与评估的基础上,利用动态贝叶斯网络进行相应的推理和预测。该策略可有效降低对抗模型的复杂度和计算量,广泛提高决策的精确性和快速性。最后,本文基于上述对抗博弈模型搭建了仿真平台,实时展示红蓝双方无人机集群对抗过程,并对上述算法的有效性进行了仿真验证。仿真结果表明,所提出的上述理论框架可以完整实现红蓝双方对抗模拟演示过程,可有效解决红蓝双方打击对抗过程中的多目标任务分配问题,并正确预测和评估对抗过程中所产生的不确定性因素。上述理论框架可为未来无人作战提供重要的理论支撑。

     

    Abstract: In recent years, the swarming confrontation problem of UAVs has been widely investigated because of its important application prospects in the military field. The main research framework of this problem involves several hot topics of complex system, such as game theory and distributed control theory. Therefore, the swarming confrontation problem has also attracted the interest of many scholars in the field of complex systems. Firstly, this paper proposes an adversarial game model based on the improved Lanchester equation to solve this problem towards the red and blue swarms. Secondly, based on the above confrontation model, a multiple-tasks assignment problem is investigated, which is derived from the above confrontation process. A brand-new assignment strategy of these UAVs for strike tasks is proposed by adaptive improvement on the basis of the traditional Kuhn-Munkres (KM) algorithm. This strategy is suitable for the red and blue parties under the adversarial environment, which can effectively complete the strike tasks and improve the confrontation ability of these UAVs. Thirdly, this paper proposes a swarming confrontation algorithm for the sake of improving the environmental suitability of each UAV, especially for dealing with the influences of a series of uncertain factors generated by the real-time process of swarming offensive and defensive confrontation. This algorithm focuses on predicting and evaluating the uncertainty generated during the confrontation process of the red and blue UAV swarms and performing corresponding reasoning and prediction through the dynamic Bayesian network, which can effectively reduce the complexity and calculation of the confrontation model and widely improve the accuracy and speed of decision-making. Finally, a real-time simulation platform is built on the above-mentioned confrontation model to illustrate the evolutionary process of red and blue UAV swarms, as well as to verify the effectiveness of the proposed algorithm. The simulation results indicate that the above framework can demonstrate the real-time offensive and defensive confrontation process of red and blue UAV swarms, effectively solve the problem of task assignment conflicts between red and blue swarms, and accurately predict and evaluate the uncertainty issues derived from the swarm confrontation process. The above research framework can provide important theoretical support for unmanned combat in the future.

     

/

返回文章
返回