基于自适应t分布黑翅鸢优化的多无人机协同路径规划OA

To address the multi-constraint coupling problem in cooperative path planning of mul-tiple unmanned aerial vehicles(UAVs)operating in mountainous terrain,this paper proposes a co-operative path planning method based on an improved black kite algorithm(IBKA)with adaptive t-distribution.The proposed algorithm introduces a dynamic elite opposition-based learning mechanism to enhance population diversity,incorporates an adaptive t-distribution mutation operator to achieve a balance between global exploration and local exploitation,and employs a Levy flight strategy to improve the ability to escape local optima,thereby establishing a highly convergent optimization frame-work.At the path generation level,a spatial partitioning strategy is adopted to reduce the complexity of three-dimensional search space,and a multi-objective function integrating flight range cost,flight altitude,and spatiotemporal collaborative constraint is designed.Through a co-evolution mechanism,the proposed method enables parallel optimization of multi-UAV trajectories.Simulation results show that,in single-UAV tasks,IBKA shortens the path length by 9.3%,12.4%,and 14.2%compared with PSO,EVO,and WOA algorithms,respectively.In multi-UAV scenarios,the proposed method generates smooth trajectories satisfying safety distance and time coordination requirements,with an average path length reduction of approximately 14.1%.The results demonstrate that IBKA exhibits superior performance under complex constraint coupling conditions and provides an efficient and prac-tical intelligent planning solution for mountain reconnaissance and emergency delivery missions.