UAV Path Planning by Fusion of Improved Ant Colony and Genetic Algorithms

Ant Colony Optimization is a widely used optimization algorithm for path planning, but speed of convergence and ease of local optimization solution finding are still two issues restricting the efficiency of the algorithm. To address these issues of ACO, a fusion algorithm by integrating the ant colony algorithm and the genetic algorithm is proposed in this paper, which is called GACA. Specifically, the genetic algorithm is adopted to find the most suitable path, which is considered as the initial path pheromone of ACO. To further enhance the optimization ability of ACO, the pheromone update mechanism is optimized. A heuristic function related to the historical iterative optimum is added to the pheromone update mechanism so that a high concentration of pheromone is distributed over shorter paths and nodes after each iteration. The heuristic function called Corner Cost is also incorporated into the transfer probability formula to make the path more fluid with fewer turning points. The experimental results demonstrate that the proposed fusion algorithm is superior to both the traditional ant colony algorithm and the genetic algorithm in terms of search efficacy.