具有方向约束的无人机改进D~*算法航迹规划

Improved D~* Algorithm for UAVPath Planning with Direction Constrains

无人机航迹规划是一种多约束的函数优化问题,特别是加入方向约束限制后更是加大问题的求解难度。传统D*算法在求解有方向约束的航迹规划问题时存在规划航程远,威胁代价高等不足。针对上述问题,提出一种结合遗传算法的改进D*算法。改进算法根据特定策略从D*规划的初始航迹中提取特征节点生成特征点路径,并以优化后的特征点路径为基础生成初始种群,设计了合理的适应度函数。仿真结果表明,所提算法规划航迹航程更短,威胁代价更小,具有一定实用价值。

Unmanned aerial vehicle （UAV） path planning is a multi-constrained function optimization problem, especially after adding the direction constraint limits, it is more difficult to solve the problem. The traditional D ＊ algorithm has many disadvantages in solving the directional constrained path planning problem, such as the long plan- ning range and the high threat costs. To solve these problems, an improved D ＊ algorithm based on the genetic algorithm （GA） is proposed. The algorithm extracted the feature nodes from the initial track of the D ＊ plan according to the specific strategy, and generated the initial population on the basis of the optimized feature point path, and then designed a reasonable fitness function. The simulation results show that the improved algorithm＇ s planning path is shorter and its threat cost is less.