蚁群优化算法的无人机室内航迹规划

Ant colony optimization algorithm for UAV indoor trajectory planning

由于室内无人机导航较为复杂,针对现有的传统(基本)蚁群算法存在早期盲目搜索、易陷入局部最优和收敛速度慢等问题,探索一种高效、准确的航迹规划方法意义重大。为提高收敛速度使其避免陷入局部最优等算法缺陷,提出一种改进蚁群算法的室内无人机三维航迹规划方法,该方法设计初始信息素的调节因子,增强蚁群搜索的方向性;设计启发概率函数,改进状态转移规则,有效提高蚁群可见性精度;改进算法的信息素更新方式,增加信息素挥发率的动态调整策略,提高算法的收敛速度,扩大搜索空间,有效避免其陷入局部最优。通过仿真实验进行算法适应性验证,结果表明:改进蚁群算法有效提高全局搜索能力,减少收敛迭代次数,得到的最优路径长度比传统蚁群算法平均缩短38.6%,平均用时减少3.8%,显著提高蚁群优化算法的适应性,体现出在特定应用场景下的优越性。

Due to the complicated indoor drone navigation,there is an early blind search for the existing traditional(basic)ant colony algorithm,which is easy to fall into a problem such as local optimization and slow convergence speed.Explore an efficient and accurate track planning method significance.In order to improve the convergence speed,it is proposed to improve the three-dimensional airline planning method for improving the ant colony algorithm.The method designs the adjustment factor of the initial pheromone,enhances the directionality of the ant colony search.The design inspiration probability function,improve the state transfer rules,effectively improve the visibility of ant colony.The updated methods of the algorithm pheromones are improved,with their dynamic adjustment strategies promoted,thus increasing the convergence speed of the algorithm,expanding search space,and effectively avoiding its topical optimal.The algorithm adaptation verification is performed by simulation experiments,and the results show that the improved ant colony algorithm effectively improves global search capabilities,reducing the number of convergence iterations,the optimal path length is less than 38.6%more than the traditional ant colony algorithm,nd the average time reduces by 3.8%.Significantly improve the adaptability of the ant colony optimization algorithm,indicating the superiority of a particular application scenario.