Based on the background of the rapid spread of COVID-19, in order to block the path of human-to-human transmission of the virus, the use of drones for "last mile" end delivery can effectively solve the problem of material supply during the epidemic isolation stage. This paper considers the range and load constraints of UAVs, establishes a distribution route optimization model with the shortest total delivery time as the goal, and designs a symbolic encoding method that conforms to the model to generate chromosomes according to the characteristics of taking first and then sending in the distribution process. The adaptive crossover and mutation probability is designed to improve the optimization ability of the genetic algorithm, and finally the simulation test is carried out. The results show that compared with the standard genetic algorithm, the improved adaptive genetic algorithm is more efficient, better quality, and has better solving ability in solving such problems.