Optimization of Vehicle-UAV Collaborative Delivery Path Based on Improved Genetic Algorithm

Jiahui Wang

doi:10.47297/taposatWSP2633-456935.20250610

PDF
Export
Share
Collection
Album

Optimization of Vehicle-UAV Collaborative Delivery Path Based on Improved Genetic Algorithm

Volume 6, Issue 10

Views: 0 Downloads: 0

Optimization of Vehicle-UAV Collaborative Delivery Path Based on Improved Genetic Algorithm
Optimization of Vehicle-UAV Collaborative Delivery Path Based on Improved Genetic Algorithm
School of Information Science and Engineering, Shandong University, Qingdao Campus, Qingdao, Shandong, 266237, China
Vol. 6, Issue 10, Pages: 173-179(2025)
Published：30 October 2025
DOI：10.47297/taposatWSP2633-456935.20250610
Accepted：

Scan QR Code

Wang Jiahui.Optimization of Vehicle-UAV Collaborative Delivery Path Based on Improved Genetic Algorithm[J].Theory and Practice of Science and Technology,2025,06(10):173-179.
DOI：

Wang Jiahui.Optimization of Vehicle-UAV Collaborative Delivery Path Based on Improved Genetic Algorithm[J].Theory and Practice of Science and Technology,2025,06(10):173-179. DOI： 10.47297/taposatWSP2633-456935.20250610.

摘要

Abstract

As urban demand for last-mile logistics grows rapidly

vehicle-UAV collaborative delivery has drawn widespread interest as an efficient distribution mode. To address the path optimization problem in the collaborative delivery of a single vehicle with two UAVs

this study proposes an optimization approach based on an improved genetic algorithm. Multi-chromosome hybrid encoding is employed to simultaneously represent the collaborative paths of the vehicle and UAVs. The algorithm's global search capability and convergence speed are enhanced by integrating elitism preservation

adaptive crossover and mutation

neighborhood transformation

and task perturbation strategies. A multi-objective optimization model is established to comprehensively consider delivery time

energy consumption

and cost

with simulation experiments conducted in the MATLAB.The experimental results demonstrate that the improved algorithm significantly reduces total delivery time

energy consumption

and costs compared to traditional single-vehicle delivery and standard genetic algorithms

while also enabling reasonable task allocation and path planning. Additionally

the algorithm shows good stability and robustness under different parameter conditions. This research offers an effective approach and theoretical reference for optimizing vehicle-UAV collaborative delivery routes in intelligent logistics systems

and has practical significance for improving the efficiency of urban last-mile delivery.

关键词

Keywords

references

Wang Y, Li J, Yang X, et al. UAV–Ground Vehicle Collaborative Delivery in Emergency Response: A Review of Key Technologies and Future Trends[J]. Applied Sciences, 2025, 15(17): 9803-9815.

Li J, Liu H, Lai K K, et al. Vehicle and UAV collaborative delivery path optimization model[J]. Mathematics, 2022, 10(20): 3744.

Zhang Q, Huang X, Zhang H, et al. Research on logistics path optimization for a two-stage collaborative delivery system using vehicles and UAVs[J]. Sustainability, 2023, 15(17): 13235.

Guo J, Song R, He S. Vehicle and onboard UAV collaborative delivery route planning: considering energy function with wind and payload[J]. Journal of Systems Engineering and Electronics, 2025, 36(1): 194-208.

Wang L, Huang W, Li H, et al. A review of collaborative trajectory planning for multiple unmanned aerial vehicles[J]. Processes, 2024, 12(6): 1272.

Jang G, Lee K. Joint Optimization of Path Planning and Cooperative Strategy for UAV–UGV Delivery[J]. IEEE Transactions on Intelligent Transportation Systems, 2025.

Chen X, Li Q, Li R, et al. UAV network path planning and optimization using a vehicle routing model[J]. Remote Sensing, 2023, 15(9): 2227.

Lambora A, Gupta K, Chopra K. Genetic algorithm:A literature review[C]//2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon).New Delhi, India: IEEE, 2019: 380-384.

Chen J, Xiao Z. Research on adaptive genetic algorithm based on multi-population elite selection strategy[C]//2017 2nd IEEE international conference on computational intelligence and applications (ICCIA). IEEE, 2017: 108-112.

Fathi M, Nourmohammadi A, HC Ng A, et al. An improved genetic algorithm with variable neighborhood search to solve the assembly line balancing problem[J]. Engineering computations, 2020, 37(2): 501-521.

Alert me when the article has been cited

Submit

Optimization of Distribution Network Reconfiguration Based on Improved Genetic Algorithm

Related Author

Zhiyu Chen Belarusian National Technical University, Minsk, 220013, Belarus

Related Institution

Belarusian National Technical University, Minsk, 220013, Belarus

⁰