Double-ant Colony Based UAV Path Planning Algorithm

Abstract

Path planning plays an important role in the applications of Unmanned Aerial Vehicles (UAVs). It allows the UAV to autonomously compute an optimal path from the initial point to the end by checking some specific control points or fulfill some mission specific constraints (e.g., obstacle avoidance, fuel consumption, etc.). While ant colony optimization (ACO) algorithm has attracted a great deal of attention due to the fact that ants can work cooperatively to find an optimal path. However, ACO converges slowly in finding an optimal path, particularly for the case when the problem domain is large. To solve this problem, a double-ant colony based algorithm is proposed in this paper. More specifically, in the early stage we exploit genetic algorithm to generate pheromones, thus accelerating the convergence of the algorithm. Numerical results validate the effectiveness of the proposed algorithm.