面向环境探测的多智能体自组织目标搜索算法

Self-organizing target search algorithm of multi-agent system for envi-ronment detection

针对在复杂非结构化环境下如何协调多个无人机发现静态或动态目标的问题,建立了自组织目标搜索算法框架。结合磁探仪等效平均探测宽度模型,受昆虫协调方式和鸟群效应的生物机制启发,提出了基于仿生集群算法的无人机集群分布式目标搜索模型;采用改进的自适应差分进化算法帮助无人机集群模型在环境中平衡勘探和探索,实现无人机群体的协同搜索优化。该自组织目标搜索算法旨在以最短时间实现跟踪目标数量的最大化。基于仿真平台的实验测试了该策略的性能,验证了算法对具有未知目标的非结构化复杂环境的适用性。

In this study, the framework of self-organizing target search algorithm was developed to coordinate unmanned aerial vehicle(UAV) swarm to find static and dynamic targets in a complex unstructured environment. First, the UAVs distributed target search model was developed from the biologically-inspired mechanisms called flocking and stigmergy, which incorporated the magnetic detector’s equivalent average width feature. Secondly, an improved differential evolution algorithm, which introduced adaptive operators, was proposed for the balancing of exploration and exploitation in the multi-UAV collaborative search system and realizing optimization of UAV collaborative search. This self-organizing target search algorithm aims at optimizing the number of tracking targets in the shortest possible time.The target search strategy tested on the simulation framework validates the algorithm’s adaptability for uncertain spatial targets in unstructured complex scenarios.