UAV path planning based on improved student mental optimization algorithm
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
万方数据
针对标准学生心理优化算法(student psychology based optimization,SPBO)在解决无人机路径规划中遇到的搜索能力欠缺、陷入局部最优等问题,提出一种改进学生心理优化算法的无人机三维路径规划.首先,为增强无人机的局部搜索能力,引入人为划分小组和分层学习方式,对学生心理优化算法中的学生群体进行更新处理.其次,为解决无人机陷入局部最优问题,借鉴蜜獾算法(honey badger algorithm,HBA)中的挖掘搜索机制来跳出局部搜索.最后,通过 MATLAB仿真实验结果表明,改进学生心理优化算法(ISPBO)的平均路径长度减少了0.127 5 km、代价平均值降低了1.94%和标准差减少了84.07%,验证了ISPBO具有更强的寻优能力和更好的稳定性.
Aiming at the problems of lack of search ability and falling into local optimization encountered by the standard student psychology based optimization(SPBO)algorithm in solving the UAV path planning,a kind of three-dimensional path planning for UAVs with improved student psychology optimization algorithm is proposed.First,in order to enhance the local search ability of the UAV,artificial group division and hierarchical learning are introduced to update the students in the student mental optimization algorithm.Secondly,in order to solve the problem of UAV falling into local optimization,the mining search mechanism in honey badger algorithm(HBA)is borrowed to jump out of local search.Finally,the results of MATLAB simulation experiments show that the average path length of the improved student psychology based optimization algorithm(ISPBO)is reduced by 0.172 5 km,the average cost is reduced by 1.94%and the standard deviation is reduced by 84.07%,which verifies that ISPBO has stronger optimization ability and better stability.
NETL
NSTL
万方数据
