To compare the performance of ant colony algorithm and artificial bee colony algorithm in UAV track planning

Abstract

In the field of unmanned aerial vehicle (UAV) trajectory planning, the optimization of intelligent algorithms is crucial. This paper compares and analyzes the search ability, convergence, and environmental adaptability of the Ant Colony Optimization (ACO) and Artificial Bee Colony (ABC) algorithms in UAV path planning. The study finds that the ABC algorithm demonstrates strong global search ability but lower local search efficiency, with fast initial convergence but a tendency to fall into local optima. The ACO algorithm excels in local search and adaptability to complex environments, though its performance declines in high-dimensional problems. Through literature review, the study reveals differences in their dynamic environment performance and proposes optimizing the local search mechanism of ABC and improving the heuristic function of ACO to enhance UAV path smoothness. This research fills the gap in traditional algorithm comparison and provides references for UAV trajectory planning algorithm optimization.