Abstract:

To satisfy the requirements of unmanned aerial vehicle (UAV) offline path planning for the algorithm's global search capability and robustness, a self-adaptive coyote optimization algorithm is designed to study UAV offline path planning from the perspective of optimization problems. A mathematical model is established for UAV offline path planning. On the basis of the coyote optimization algorithm, four operators and an adaptive learning mechanism are designed to enable the algorithm to intelligently select the appropriate operator during the search process, and design the Levy flight strategy to improve the algorithm's global search ability. Finally, the function test and offline path planning simulation are carried out for the self-adaptive coyote optimization algorithm. The function test shows that the self-adaptive coyote optimization algorithm has a strong global search ability, and the offline path planning simulation shows that the self-adaptive coyote optimization algorithm can adapt to the offline path planning problem of different dimensions.

Key words: unmanned aerial vehicle (UAV), path planning, coyote optimization algorithm, self-adaptive learning mechanism, Levy flight