论文部分内容阅读
为了解决无人机在部分未知敌对环境中的低空突防航迹规划问题,提出了一种改进的差分进化算法.该算法的进化模型采用冯.诺伊曼拓扑结构,并对其进行拓展,使种群在进化初期保持多样性,避免进化早期陷入局部最优,而进化后期加快收敛速度.该算法改进了差分进化算子中的变异操作,从而加快算法的收敛速度,快速找到多目标优化问题的最优解;同时,采用将绝对笛卡儿坐标和相对极坐标相结合的编码方式以提高搜索效率.将该算法用于无人机在线航迹规划仿真实验,并和未改进的算法结果作比较,验证了该算法的有效性.
In order to solve the problem of low-altitude pedestrian trajectory planning in some unknown hostile environments, an improved differential evolution algorithm is proposed. The evolutionary model of the algorithm uses von Neumann topology and extends it. So as to keep the population diversity in the early evolutionary stage and avoid the local evolution in the early stage of evolution and accelerate the convergence in the late evolutionary stage.The algorithm improves the mutation operation in the differential evolution operator to speed up the convergence of the algorithm and quickly find the multi-objective optimization problem And the optimal combination of absolute Cartesian coordinates and relative polar coordinates is used to improve the search efficiency.The algorithm is applied to the simulation experiment of UAV flight path planning and is compared with the unmodified algorithm For comparison, the effectiveness of the algorithm is verified.