Aiming at the problems of low convergence accuracy and local optimization of heuristic algorithm in Unmanned Aerial Vehicle (UAV) path planning, an Adaptive Osprey Optimization Algorithm (AOOA) is proposed. Firstly, Bernoulli chaotic mapping is used to improve the population diversity effectively. Secondly, adaptive cosine factor is introduced to balance the global search ability and local development ability, and in combination with Levy flight strategy, the step size is adjusted adaptively to help the individual osprey better jump out of the local optimal. Then, the refraction reverse learning strategy is used to improve the quality of the global optimal solution, and the convergence accuracy and speed are improved to a certain extent. After that, the performance of the algorithm is compared with that of other 5 algorithms in 15 CEC2005 test functions, and the results show that the algorithm has excellent performance in convergence accuracy and stability. Finally, it is transplanted to the UAV path planning problem and tested under the terrain obstacle models with 6, 9 and 12 peaks. The simulation results show that, compared with other algorithms, AOOA has lower average cost, lower standard deviation, and shorter and more stable path in different terrain scenarios.