基于TGWO的无人机三维路径规划OA

To address the unmanned aerial vehicle(UAV)path planning problem in complex environments,this paper pro-poses an improved grey wolf optimizer(TGWO)algorithm to overcome the limitations of traditional GWO,including insufficient population diversity,limited global search capability,and a tendency to fall into local optima.In terms of algo-rithm design,the Tent chaotic mapping is introduced to enhance the uniform distribution of the initial population,thereby improving the diversity of global search.A perturbation mechanism inspired by the sparrow search algorithm(SSA)is incorporated to strengthen the adaptability and global exploration ability of GWO.A Cauchy-Gaussian composite muta-tion strategy is adopted to achieve a better balance between global exploration and local exploitation,effectively enhancing the algorithm ability to escape local optima.For experimental validation,benchmark function tests are conducted to evaluate the optimization performance of TGWO.Simulation studies are carried out under three different task environments:static no-fly zones,dynamic no-fly zones,and multi-UAV cooperative control scenarios.The results demonstrate that,in the static no-fly zone scenario,the TGWO algorithm achieves significant improvements in path planning performance compared with GWO,DBO,MOGWO,and MOEA/D algorithms.Moreover,in the dynamic no-fly zone and multi-UAV coopera-tive control scenarios,TGWO continues to exhibit excellent planning capability and stability,fully demonstrating its robustness and adaptability in complex environments.