论文部分内容阅读
提出了一种基于小生境遗传算法的飞行航迹规划方法。把航迹编码为离散时间上变长度的飞行器速度和航向变化序列,并以此序列作为遗传算法种群中的个体,在这个变化序列中,每一个元素都考虑了飞行器的性能约束,因而,每个变化序列对应的航迹都是飞行器可飞的。初始种群不是随机生成,而是根据规划起点和终点的相对关系生成的。为了防止种群收敛于局部最优解,采用基于共享函数的小生境技术增加种群的多样性。仿真结果表明,算法能快速有效地在动态环境中规划出近最优的飞行航迹。
A method of flight path planning based on niche genetic algorithm is proposed. The trajectory is encoded as a sequence of aircraft velocities and heading changes with discrete time up-scaling, and this sequence is used as an individual in a population of genetic algorithms. In this sequence of changes, each element takes into account the performance constraints of the aircraft. Thus, each The trajectories corresponding to a series of changes are aircraft flyable. The initial population is not randomly generated, but rather generated from the relative relationship between the planning start and end points. In order to prevent the population from converging to the local optimal solution, niche techniques based on shared functions are used to increase the diversity of the population. The simulation results show that the algorithm can quickly and efficiently plan the near optimal flight path in dynamic environment.