基于透镜成像对立学习TSO算法的无人机三维航迹规划

3D Path Planning of UAVs Based on Lens Imaging Opposite-Learning TSO

金枪鱼优化算法求解无人机三维航迹规划容易出现搜索精度差、航迹代价高的问题,为此设计了基于透镜成像对立学习机制的改进金枪鱼优化算法。首先,引入非线性权重系数更新、最优最差对立学习及透镜成像对立学习策略对金枪鱼优化算法寻优性能进行改进,提升算法逼近最优解的精度;然后,建立具有地貌约束和性能约束的障碍物威胁模型,将无人机三维航迹规划问题转换为代价函数优化问题,利用改进算法迭代求解航迹规划,搜索代价最小且安全避障的最优航迹。实验结果表明,改进算法有效解决了原有早熟收敛问题,其规划航程更短、代价更低,且航迹规划效率得到了有效提升。

The Tuna Swarm Optimization(TSO)algorithm is easy to have poor search accuracy and high path cost when used for three-dimensional path planning of UAVs.Therefore,an improved TSO algorithm is designed based on lens imaging opposite-learning mechanism.Firstly,nonlinear weight coefficient updating,the best and worst opposite learning,and lens imaging opposite learning strategies are introduced to optimize the performance of the TSO algorithm and to improve its accuracy when approaching the optimal solution.Then,a threat model with geomorphic constraints and performance constraints is established,and the 3D path planning problem of UAV is converted into an optimization problem of cost function.The improved algorithm is used to iteratively solve the path planning,and search for the optimal,safe and obstacle-avoiding path with the minimum cost.Simulation results of path planning show that,the improved algorithm effectively solves the premature convergence problem,and its planned path is shorter with lower cost,and the planning efficiency is improved.