| Περίληψη: |
Unmanned aerial vehicle (UAV) global path planning in static environments aims to find the optimal or feasible path between the starting and ending points, which is related to the efficiency and safety of UAV’s task execution. Thus, UAV path planning has received wide attention. Existing path planning methods such as the artificial bee colony (ABC) algorithm are susceptible to local optima and suffer from insufficient local exploitation. To address these problems, this paper proposes a novel UAV path planning method that combines the ABC algorithm with differential evolution (DE), referred to as ABCDE. First, during the initialization phase, the DE/rand/1 strategy is incorporated to optimize the initial population, thereby reducing invalid solutions. Second, in the scout bee phase, a hybrid approach that combines the DE/rand/1 and DE/best/1 strategies is adopted, with strategy selection dynamically adapted to the algorithm’s iteration progress. This effectively addresses the problems of weak local exploitation capability and susceptibility to local optima. Finally, simulation experiments are conducted, including randomly generated urban and mountainous terrain scenarios, to perform a comparative analysis of path planning performance across different scenes and algorithms. Experimental results show that compared with the ABC, the PSO, the GA, and the improved ABC (IABC) algorithms, the proposed method reduces path lengths by 4.33%, 3.15%, 17.04%, and 2.40%, respectively, in both urban and mountainous terrain environments and improves the quality of path planning and the local exploitation capability. [ABSTRACT FROM AUTHOR] |