Research on the Path Optimization Model for Low-Altitude Logistics of Heavy-Load Drones Based on Genetic Algorithm

Abstract

Low-altitude logistics could indicate a significant application scenario within the broader low-altitude economy. Moreover, the findings may suggest that heavy-payload unmanned aerial vehicles demonstrate considerable potential in emergency delivery, remote-area supply, and medical distribution contexts. However, the evidence appears to show that route planning remains constrained by payload capacity, flight range, task point distribution, and energy consumption. In light of these key constraints, the study may suggest that a multi-task-point delivery scenario provides the relevant framework for constructing a route optimization model. Route optimization shows payload, range, task demands matter. Furthermore, the results could indicate that minimization of total flight distance serves as the critical optimization objective within this established model. Additionally, the significant evidence may suggest that a genetic algorithm based on natural-number encoding, order crossover, swap mutation, and a penalty function appears to support robust simulation experiments. Nevertheless, the important findings might demonstrate that the results show the optimal total flight distance obtained by the genetic algorithm could indicate superiority over those generated by the random routing method and the nearest-neighbor algorithm. Notwithstanding these results, the evidence may suggest that the algorithm also appears to support reductions in delivery time and estimated energy consumption. Genetic algorithm outperforms alternatives. Thus, the study may suggest that the findings provide a useful reference for route planning and scheduling decisions in low-altitude logistics.