基于协进化机制的多传感器协作方法  

Study of multi-sensor cooperative method based on co-evolution mechanism

作　　者：张强[1,2] 杨昌昊[3] 

机构地区：[1]合肥工业大学过程优化与智能决策教育部重点实验室,安徽合肥230009 [2]合肥工业大学计算机网络系统研究所,安徽合肥230009 [3]中国科学技术大学精密机械与精密仪器系,安徽合肥230027

出　　处：《合肥工业大学学报（自然科学版）》2009年第9期1338-1342,共5页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(70801024);安徽省自然科学基金资助项目(070416241)

摘　　要：多传感器之间如何产生动态、鲁棒的适应性协作行为以完成共同的任务,是多传感器协作的主要研究内容之一;文章在基于行为的多传感器系统的基础上,设计了基于协同进化机制的多传感器协进化模型及其协进化决策算法,使系统在协进化机制的控制下能分布并行地协同进化各传感器基本行为策略库,形成传感器适应性的协作行为以完成共同的任务;最后通过对无人侦察机编队协作侦察移动目标的仿真实验表明,能够有效地解决多传感器之间的协同问题。How to form dynamic, robust and adaptive cooperation behavior between multiple sensors to complete the common task is one of the main research areas on multi-sensor cooperation. Based on behavioral multi-sensor systems, a co-evolution model based on the co-evolution mechanism as well as its co-evolution decision algorithm is established, which enables the basic behavior strategy library of each sensor to parallelly and distributedly co-evolve when the system is under the control of co-evolution mechanism, thus forming adaptive cooperation behavior to complete the common task. Finally, a simulation experiment on multiple-UCAVs scouting cooperation is carried out. The result shows that the model and algorithm can effectively solve the multi-sensor cooperative problem.

关 键 词：协进化机制 多传感器协作 协进化决策算法 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]