基于改进袋獾优化算法的无人机路径规划

Path Planning of UAV Based on Improved Tasmanian Devil Optimization Algorithm

无人机(UAV)路径规划的目标是在考虑地形威胁和高度约束的条件下,得到一条尽可能高效的安全飞行路径。袋獾优化算法是一种模拟袋獾进食的两种行为来寻求最优解的元启发式算法。在袋獾优化算法(TDO)的基础上,结合自适应权重方式减少陷入局部最优的情况,还引入limit阈值思想,可以更好地平衡全局搜索和局部收敛。首先通过六个测试函数,将改进后的算法与多种算法进行对比实验,验证算法的高效性。然后建立两个不同的地图模型,将三维路径的长度视为适应度函数,通过与粒子群算法、人工鱼群算法及蚁群算法共同求解三维路径规划问题,验证改进算法的可行性。实验结果表明,改进后的算法有更快的收敛速度和更高的收敛精度,不易陷入局部最优,而且在三维路径规划问题中具有更好的求解能力。

The goal of Unmanned Aerial Vehicle(UAV)path planning is to obtain a safe flight path that is as efficient as possible con-sidering terrain threats and altitude constraints.Tasmanian Devil Optimization(TDO)is a meta-heuristic algorithm that simulates two feeding behaviors of Tasmanian devils to find the optimal solution.Tasmanian Devil Optimization and adaptive weighting approach are combined to reduce the situation of falling into local optimum,and the idea of limit threshold is also introduced,which can better bal-ance the global search and local convergence.The proposed algorithm is compared with a variety of algorithms on six test functions.Then two different map models are established and the length of the 3D path is considered as the fitness function to verify the feasibility of the improved algorithm by solving the 3D path planning problem together with particle swarm algorithm,artificial fish swarm algorithm and ant colony algorithm.The simulation results confirm that the improved algorithm has faster convergence speed and higher conver-gence accuracy,and it is not easy to fall into local optimum in later exploration.The algorithm has better solving ability in 3D path plan-ning problems.