Intelligent Last-Mile Delivery Route Optimization in Smart Logistics: Application Value and Development Pathways

DOI: https://doi.org/10.62517/jbm.202609504

Author(s)

Ying Wang, Guohua Cheng*

Affiliation(s)

School of Digital Economy and Management, Guangdong University of Science and Technology, Dongguan, Guangdong, China *Corresponding Author

Abstract

As smart logistics continues its digital transformation, last-mile delivery has become the final and most critical link in the logistics service chain. Its operational effectiveness directly affects enterprises' cost-control outcomes and customer service experience. Urban last-mile delivery today is marked by fragmented orders, scattered delivery points, and rigid time requirements. The traditional model, which relies on experience-based route scheduling, suffers from low resource utilization, high delivery costs, and weak dynamic adaptability. It struggles to meet the demands of high-quality modern logistics. To tackle these operational pain points, this paper centers on intelligent optimization of last-mile delivery routes. Drawing on the current state of smart logistics, it examines the diverse application value of intelligent route optimization models, analyzes the practical dilemmas that arise as the industry moves toward intelligentization, and proposes viable long-term development pathways in light of digitalization trends. The goal is to offer practical references for small and medium-sized logistics enterprises as they pursue intelligent upgrading of last-mile delivery, improve route scheduling systems, and enhance both quality and efficiency. In doing so, the study contributes to the standardized, refined, and sustainable development of smart last-mile logistics systems.

Keywords

Smart Logistics; Last-Mile Delivery; Route Optimization; Intelligent Upgrading; Logistics Quality and Efficiency Enhancement

References

[1] Zhang Jingling, Zhao Yanwei. A Review of Research on Vehicle Routing Optimization Problems. Journal of Mechanical Engineering, 2010, 46(20): 1-11. [2] Liu Gang. Research on Urban Last-Mile Logistics Delivery Route Optimization Based on Artificial Intelligence Algorithms. Logistics Technology, 2021, 40(05): 88-92. [3] Wang Jing, Chen Huaili. A Review of Research on Delivery Route Optimization for Small and Medium-Sized Logistics Enterprises. Logistics Sci-Tech, 2022, 45(06): 112-115. [4] Duan Zhengyu, Yang Dongyuan. Research Progress on Dynamic Route Optimization for Urban Delivery Vehicles. Journal of Traffic and Transportation Engineering, 2020, 20(03): 1-16. [5] Ma Xin, Zhu Jianrong. Delivery Route Optimization Based on Heuristic Algorithms in the Context of Smart Logistics. Journal of Commercial Economics, 2023(08): 147-150. [6] Ge Xianlong, Wang Xu, Deng Lei. Research Progress on Dynamic Vehicle Routing Problems. Computer Integrated Manufacturing Systems, 2013, 19(02): 312-320. [7] Wang Jian, Lin Hang. Research on Urban Delivery Route Optimization and Low-Carbon Development from the Perspective of Green Logistics. Logistics Engineering and Management, 2022, 44(07): 112-114. [8] Li Yang. An Analysis of the Dilemmas and Pathways of Digital Transformation for Small and Medium-Sized Logistics Enterprises. Logistics Sci-Tech, 2023, 46(02): 108-110. [9] Feng Jia, Li Ming. Research on New Energy Delivery Vehicles Empowering the Development of Urban Intelligent Last-Mile Logistics. Journal of Commercial Economics, 2024(03): 151-153 [10] Plazier P, Rauws W, Neef R, et al. Towards sustainable last-mile logistics? Investigating the role of cooperation, regulation, and innovation in scenarios for 2035. Research in Transportation Business & Management, 2024, 56:101198. [11] Mahmoodi A, Easa S M. A multi-objective matheuristic framework for sustainable truck-UAV last-mile delivery in smart urban built environments. Smart and Sustainable Built Environments, 2026, 15 (2):412-430. [12] Guan Q F, Fan Y P, Wang Y J, et al. Real-time multi-depot urban logistics optimization in megacities via transformer-based deep reinforcement learning. International Journal of Geographical Information Science, 2026, 40 (5):987-1012.