国防基础计划项目; 河北省重点研发计划项目(19250801D); 河北省研究生创新资助项目(CXZZSS2020098); 河北省军民融合发展研究课题(HB19JMRH009)
In order to solve the problem that ant colony algorithm is easy to fall into local optimum in UAV route planning, an improved ant colony algorithm was proposed. The upper and lower limits of pheromone volatilization factor and pheromone were set to prevent ants from falling into local optimum because pheromone on short path was too high or pheromone on long path was too low. At the same time, under the influence of multiple heuristic factors, the overall length of the path was taken as an adaptive heuristic function factor to determine the state transition probability. When the path length was large, the adaptive heuristic function factor was small, which reduced the probability of choosing the path by the ant colony. The experimental results show that the improved algorithm reduces the path length by 6.4% and the variance of the optimal path length by 85.78%, which increases the consideration of environmental integrity, shortens the path length, reduces the number of iterations, and jumps out of the local optimum. In the case of increasing environmental complexity, the algorithm can effectively choose a better path and provide a theoretical basis for UAV route planning after introducing the adaptive heuristic function factor.