Learning-Based Heterogeneous Autonomous Vehicles Scheduling for On-Demand Last-Mile Transportation
- 18 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 21195-21211
Abstract
Last-mile transportation, a critical component of public transit within integrated urban mobility systems, plays a pivotal role in promoting sustainability and requires immediate attention. However, due to the high real-time variability and uncertainties of last-mile travel demand, high passenger concurrency, and dispersed destinations, existing last-mile transportation systems often encounter significant challenges. These challenges include resource shortages and congestion during peak hours, as well as high operational costs and excessive passenger waiting times during off-peak periods. With the rapid development and widespread adoption of autonomous vehicles, which are characterized by centralized control and flexible scheduling, this study proposes leveraging heterogeneous autonomous vehicles to address these challenges. Specifically, a mixed-integer programming model is developed to maximize the service provider’s profit by considering fare profit, passenger waiting time penalties, and operating costs. To enable real-time decision-making, then an attention-based deep reinforcement learning algorithm is introduced. This algorithm incorporates two decoder mechanisms for vehicle selection and passenger allocation in the scheduling of heterogeneous autonomous vehicles. This involves dynamically selecting vehicles from a heterogeneous fleet based on passenger demand using an attention mechanism, optimizing efficiency in serving last-mile travelers. Extensive numerical experiments and a real-world case study across various datasets demonstrate that the proposed service model and algorithm effectively solve the scheduling problem while meeting the demands of on-demand last-mile transportation. Furthermore, these innovations contribute to reducing fleet carbon emissions and advancing sustainable urban transportation.Keywords
Funding Information
- National Natural Science Foundation of China (71974043, 72174042)
- Natural Science Foundation of Guangdong Province (2023A1515011402)
- Natural Science Foundation of Shenzhen Municipality (JCYJ20230807140406013)
This publication has 77 references indexed in Scilit:
- Selecting fast algorithms for the capacitated vehicle routing problem with machine learning techniquesNetworks, 2024
- Trust, risk perception, and intention to use autonomous vehicles: an interdisciplinary bibliometric reviewAI & SOCIETY, 2024
- From Test Sites to Public Roads - A Look at the Global Status of Shared Autonomous VehiclesATZ worldwide, 2024
- Integrating reinforcement-learning-based vehicle dispatch algorithm into agent-based modeling of autonomous taxisTransportation, 2023
- Risk-informed decision-making and control strategies for autonomous vehicles in emergency situationsAccident Analysis & Prevention, 2023
- Estimation of Route Choice Behaviors of Bike-Sharing Users as First- and Last-mile Trips for Introduction of Mobility-as-a-Service (MaaS)KSCE Journal of Civil Engineering, 2022
- Data-driven shuttle service design for sustainable last mile transportationAdvanced Engineering Informatics, 2021
- A novel reinforcement learning-based hyper-heuristic for heterogeneous vehicle routing problemComputers & Industrial Engineering, 2021
- First-and-last mile solution via bicycling to improving transit accessibility and advancing transportation equityCities, 2020
- The fleet size and mix vehicle routing problemComputers & Operations Research, 1984