军事协同巡检路线优化策略

为提高大规模多机器人巡检系统的工作效率，提出了改进的协同蚁群优化算法。该算法为每个巡检机器人设定一个路线优化蚁群，采用共享禁忌表的方式实现不同蚁群之间的信息共享，不同蚁群中的人工蚁采用代价竞争机制进行巡检节点选择，完成路线协同优化。协同蚁群优化算法能够根据巡检节点的分布完成巡检区域的分割与路线优化，提高了巡检区域划分的合理性。仿真实验结果表明，与基于地图分割的优化算法相比，协同蚁群优化算法能够根据巡检任务对巡检区域进行均衡划分，提高了巡检机器人的利用率，减少了整体巡检量，巡检效率得到了显著提升。

Route Optimization Strategy of Military Cooperative Inspection

An improved cooperative ant colony optimization algorithm is proposed to enhance the inspection efficiency of large-scale inspection system with multiple robots. Each robot has an ant colony to search its inspection path, and a sharing taboo list is designed to implement the information interaction among the different ant colonies. The cost competitive mechanism is used to determine an ant among different ant colonies to search the inspection node. According to the distribution of the inspection nodes, the cooperative ant colony optimization algorithm could be used to accomplish the region segmentation and the path optimization simultaneously. Thus the inspection region could be segmented reasonably. Experimental results show that the cooperative ant colony optimization algorithm could be used to segment the inspection task more evenly than the conventional method based on map segmentation, which enhances the utilization rate of inspection robots, and the total inspection workload could be reduced. Therefore, the inspection performance could be improved significantly.