基于改进ACS算法的复杂环境多目标路径规划研究  

Research on multi-objective path planning in complex environment based on improved ACS algorithm

作　　者：刘健[1] 沈芸亦 邱锦 罗亚松 LIU Jian;SHEN Yunyi;QIU Jin;LUO Yasong(Ordnance Engineering College,Naval University of Engineering,Wuhan 430033,China)

机构地区：[1]海军工程大学兵器工程学院,武汉430033

出　　处：《兵器装备工程学报》2022年第S02期169-177,共9页Journal of Ordnance Equipment Engineering

基　　金：全军军事类研究课题(JY2020B117)。

摘　　要：为避免蚁群系统(ACS)算法易陷入局部最优、路径折点多的缺陷,实现特种无人车在复杂环境下行驶的安全性强、时间短、隐蔽性好等目标,提出了一种改进ACS复杂环境多目标路径规划算法。在2.5维栅格地图下基于变异系数法对单元格中的地形信息进行综合评价并得到地形信息综合评价值,在此基础上对基本ACS算法进行改进,增加可选节点优化规则改进蚂蚁选择节点的方式,并使用加入高程信息的A*算法和地形信息综合评价值改进转移概率。仿真结果表明改进的ACS算法能优化路径的安全性、隐蔽性和无人车的行驶时间,算法具有有效性。Aiming at the problems that ant colony system(ACS)algorithm is easy to fall into local optimization or many path inflection points,and in order to achieve the goals of strong safety,short time and good concealment of special unmanned vehicle driving in a complex environment,this paper proposes an improved ACS multi-objective path planning algorithm in a complex environment.Under the 2.5-dimensional grid map,the terrain information in the cell is comprehensively evaluated based on the variation coefficient method and the comprehensive evaluation value of terrain information is obtained.On this basis,the basic ACS algorithm is improved by adding optional node optimization rules to improve the way ants select nodes,and the A*algorithm with elevation information and the comprehensive evaluation value of terrain information are used to improve the transfer probability.The simulation results show that the improved ACS algorithm can optimize the security and concealment of the path and the travel time of the unmanned vehicle,which proves that the algorithm is effective.

关 键 词：无人车 蚁群系统算法 路径规划 多目标 变异系数法 

分 类 号：TJ81[兵器科学与技术—武器系统与运用工程] TP242.6[自动化与计算机技术—检测技术与自动化装置]