| 摘要: |
| 针对现有的无人机航迹规划方法收敛速度较慢、效率不高、易陷入局部最优等问题，构建了基于改进细菌觅食优化算法的无人机航迹规划结构，从三个方面改进算法：一是将固定步长改为自适应步长；二是游动时嵌入粒子群算法学习因子思想；三是将固定迁徙概率改为自适应迁徙概率。同时，提出了飞行代价目标函数，通过函数寻优进行无人机航迹规划，并由数字高程数据建立三维环境，对比基本细菌觅食优化算法和粒子群算法进行仿真。结果表明，基于改进细菌觅食优化算法优化的无人机航迹规划结构具有路径长度更短、路径更平滑和收敛速度更快的特点。 |
| 关键词: 无人机 航迹规划 改进细菌觅食优化算法 融合算法 |
| DOI： |
|
| 基金项目:国家自然科学基金民航联合研究基金（U1633127）；四川省科技基金重点项目（2020YFG0449）；中国民用航空飞行学院科研基金（CJ2020-01, JG2019-22）；大学生创新创业训练计划项目（S201910624059） |
|
| UAV track planning with improved bacterial foraging optimization algorithm |
| WEI Yongchao,DENG Lan,LI Tao,DENG Yi,DENG Chunyan |
| (Department of Research,Civil Aviation Flight University of China,Guanghan 618307,China;CAAC Academy of Flight Technology and Safety,Civil Aviation Flight University of China,Guanghan 618307,China;School of Civil Aviation Safety Engineering,Civil Aviation Flight University of China,Guanghan 618307,China) |
| Abstract: |
| For the problems such as slow convergence speed,low efficiency and easy to fall into local optimum in the existing unmanned aerial vehicle(UAV) track planning methods,the UAV trajectory planning structure is built based on the improved Bacterial Foraging Optimization(BFO) algorithm.The algorithm is improved from three aspects:first,changing the fixed step size to adaptive step size;second,embedding the learning factor idea of particle swarm algorithm when swimming;third,changing the fixed migration probability to the adaptive migration probability.In addition,the UAV track planning is performed through function optimization when the flight cost objective function is designed,and the three-dimensional environment is established from the digital elevation data.Compared with the basic BFO algorithm and the particle swarm algorithm for simulation,the results show that the UAV track planning optimized structure based on the improved BFO algorithm has the characteristics of shorter path length,smoother path and faster convergence speed. |
| Key words: UAV track planning improved bacterial foraging optimization algorithm fusion algorithm |
