关键词: 无人机, 路径规划, 秘书鸟优化算法, 随机惯性权重, 鲸鱼优化算法, 透镜成像反向学习

Abstract: Aiming at the issues of low convergence accuracy and local optima trapping, in the heuristic algorithm for solving path planning issues of unmanned aerial vehicle (UAV), an improved secretary bird algorithm based on multi-strategy (ISBOA) is proposed. Firstly, a prey consumption strategy with random inertia weight is proposed to improve the search randomness and avoid local optima trapping. Secondly, the whale algorithm encirclement strategy is introduced into the secretary bird's camouflage strategy to coordinate global exploration and local development capabilities. Finally, the secretary bird escape strategy of convex lens imaging reverse learning is adopted to improve the quality of the optimal solution and improve the convergence accuracy and convergence speed. The improved algorithm is compared with other algorithms in 15 CEC2005 test functions and UAV path planning problems. The experimental results show that the performance of the improved secretary bird algorithm is more stable and the accuracy is higher, and the UAV path planned in different mountain terrain environments is shorter and smoother.

Key words: UAV, Path planning, Secretarial bird optimization algorithm, Random inertia weight, Whale optimization algorithm, Lens imaging reverse learning