An improved ant colony optimization algorithm for the plant protection unmanned aerial vehicle path planning in terraced field environments
Youxi Long, Kecheng Tu, Yuzhong Luo · 2024
In terraced environments, path planning for the plant protection unmanned aerial vehicle (UAV) is important for reducing energy consumption. Due to its adaptability and simplicity in merging with other algorithms, the ant colony optimization (ACO) algorithm is frequently utilized in path planning. Nonetheless, it still has issues with delayed convergence and a propensity to enter a local optimum. In this paper, an modified ACO (IACO) is proposed for path planning of plant protection UAVs in terraced field environments. A pheromone concentration gradient is designed to quicken the algorithm's convergence by associating the pheromone initialization with the distance from each node to the target location. Concurrently, the path's height and length are taken into account by the optimized heuristic function, which enhances the search's targeting. Furthermore, to balance the global exploration and local search, two heuristic factors are improved: the information heuristic factor and the expectation heuristic factor, which are dynamically changed based on the number of iterations. After simulation experiments, the path length and fitness value solved by IACO are better than other algorithms, which further proves the effectiveness of IACO for plant protection UAVs in path planning in terraced environments.