基于改进蜣螂算法的无人机航迹规划

Unmanned Aerial Vehicle Flight Path Planning Based on Improved Dung Beetle Algorithm

针对无人机航迹规划求解计算量大、收敛难等问题,提出了一种融入了混沌映射和莱维飞行的多策略蜣螂优化(Piecewise Levy Flight Dung Beetle Optimizer, PLDBO)算法的航迹规划方法。建立了三维任务空间模型和无人机路径规划成本函数,将路径规划问题转化为多维函数优化问题。对蜣螂优化(Dung Beetle Optimizer, DBO)算法调用Piecewise混沌映射,改变其初始化过程,增强种群的多样性,加快收敛速度。引入黄金正弦改进滚球蜣螂位置更新公式,有效协调了全局搜索能力与局部挖掘能力,加快了收敛速度。在小偷蜣螂位置更新公式引入Levy策略,增强算法跳出局部最优的能力。引入了一种具有策略自适应的横向交叉,提高了算法的收敛精度,增强了全局寻优能力。通过将提出的改进算法在知名的15个经典基准函数上比较,全面验证了PLDBO算法的优越性,并应用于航迹规划问题求解。仿真结果表明,PLDBO算法能获得更可行、更高效的路径。

A Piecewise Levy Flight Dung Beetle Optimizer(PLDBO)is proposed to solve the problems of UAV flight path planning,which requires a lot of computation and is difficult to converge.Firstly,a 3D mission space model and the UAV path planning cost function are established,and the path planning problem is transformed into a multidimensional function optimization problem.Secondly,the Piecewise chaotic mapping is invoked on Dung Beetle Optimizer(DBO)algorithm to change its initialization process,enhance the diversity of the population,and accelerate the convergence speed.Then,the golden sine is introduced to improve the position update formula of dung beetle,which effectively coordinates the global search ability and local mining ability,and speeds up the convergence.Levy strategy is introduced into the thieving dung beetle position update formula to enhance the ability of the algorithm to jump out of the local optima.Then a horizontal crossover with adaptive strategy is introduced to improve the convergence accuracy of the algorithm and enhance the global optimization ability.Finally,the advantages of PLDBO are fully verified by comparison on 15 well-known classical benchmark functions,and the proposed algorithm is applied to the path planning problem.The simulation results show that PLDBO can obtain more feasible and efficient paths.