Abstract
In order to solve the obstacle avoidance path planning problem of multiple UAVs in complex mountainous environments, the ant colony algorithm is combined with the particle swarm algorithm and simulated annealing algorithm to propose a multiple UAV path planning algorithm based on the improved ant colony algorithm (PS-ACO-SA) to solve the path planning problem of multiple UAVs in power inspection. To ensure that multiple UAVs can complete the power inspection task efficiently, we designed a collaborative inspection model and transformed the path planning into an optimization problem that includes inspection efficiency, obstacle avoidance and other safety operation requirements and constraints by establishing a cost function. Secondly, the pheromone-related factors of the ant colony algorithm are adjusted, and the influence of the optimal path is enhanced by combining individual fitness to improve the path planning effect. The particle swarm algorithm is integrated to adjust the learning factor to improve the global search ability and speed, and the simulated annealing algorithm is introduced to increase the diversity of solutions. In order to evaluate the performance of the PS-ACO-SA algorithm, six different terrain scenarios are designed for verification. The results show that this method can improve the algorithm’s search ability, convergence speed, robustness and solution quality, and can also find better paths.
Get full access to this article
View all access options for this article.