摘要
针对目前采用蚁群算法求解无人机二维航迹规划问题需要构建VORONOI图或设置导航节点的问题,构造了可自动搜索航迹的蚁群算法,解决了该算法应用于航迹规划的两个构造难题:航迹节点不固定及局部搜索到达目标节点困难。并将导引因子引入到状态转移策略当中,减少了蚂蚁局部搜索的盲目性,确保蚂蚁最终完成航迹搜索。此外,采取当前最优航迹信息素更新策略,同时设置信息素上下限,在提高算法速度的同时,防止算法陷入局部最优。仿真结果表明,算法构造非常合理,在没有设置导航节点及VORONOI图的情况下,蚂蚁自动寻找到目标节点,且收敛速度快。
At present,it needs to build VORONOI map or set the navigation nodes for getting optimal UAV,two-dimensional path planning by adopting ACO algorithm.A new structure herein of ACO can automatically search flight path.Two construction difficulties were solved.First,path node was not fixed,that is to say it was not a simple combinatorial optimization problem.Second,it was difficult for local search to reach the destination node.And a guidance factor was included into the state transition strategy,and it can reduce the blindness of local search and ensure ants to reach the destination node.In addition,pheromone was updated just for the optimal flight path,and by setting pheromones limits between the upper and lower,it can improve the searching speed,and prevent the algorithm into a local optimum.Simulation results show that the algorithm structure is very reasonable and in the absence of navigation nodes and VORONOI map,the ants automatically seek to the target node,and the convergence speed is quick.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2011年第3期322-325,共4页
China Mechanical Engineering
基金
国家自然科学基金资助项目(60974105)
航空科学基金资助项目(2009ZC52041)
关键词
蚁群算法
航迹规划
无人机
威胁代价
油耗代价
导引因子
ant colony optimization（ACO） algorithm
path planning
unmanned aerial vehicle（UAV）
threat cost
fuel cost
guidance factor
