研究无人机航路,要在有限的时间内规划出最优路径。因此航路规划问题本质是多约束条件下函数求极值的优化问题,为了避免局部最优、减少计算时间是目前航路规划的关键技术。针对常用的规划算法存在收敛速度慢且易陷入局部最优这一问题,提出了一种改进的遗传蚁群算法。遗传算法阶段给出了一种小变异和引入新种群算子,维持了较优种群的多样性,蚁群算法阶段设计了一种基于航路代价的初始信息素获取规则,保证蚁群具有较好的初始信息素分布,在求解时能够避免陷入局部最优。仿真结果表明,与其它算法相比,提出的改进算法收敛速度大大提高,能在更短的时间规划出更优的航路。 To study the UAV route, it is necessary to plan the optimal path within a limited time. Therefore, the essence of the route planning problem is to optimize the function under the condition of multiple constraints. In order to avoid the local optimum and reduce the calculation time, it is the key technology of the current route planning. Aiming at the problem that the commonly used algorithms have slow convergence speed and easily fall into local optimum, an improved genetic ant colony algorithm is proposed. Genetic algorithm stage gives a small mutation and introduces a new population operator to maintain the diversity of the superior population. The ant colony algorithm phase design an initial pheromone acquisition rule based on route cost to ensure that the colony has better Of the initial pheromone distribution, in solving can avoid falling into the local optimum. The simulation results show that compared with other algorithms, the improved algorithm proposed in this paper can greatly improve the convergence speed and can plan a better route in a shorter time.