EURO 2025 Leeds
Abstract Submission

2874. Attention Model for Time Slot Management Vehicle Dispatching Problem

Invited abstract in session MB-27: Vehicle Routing under Uncertainty , stream Stochastic and Robust optimization.

Monday, 10:30-12:00
Room: Maurice Keyworth G.02

Authors (first author is the speaker)

1. Sifanur Celik
Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology
2. Albert Schrotenboer
Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology
3. Layla Martin
Operations, Planning, Accounting and Control, Eindhoven University of Technology
4. Tom van Woensel
Technische Universiteit Eindhoven

Abstract

The rapid growth of e-commerce has raised customer expectations for faster and more reliable delivery services, making same-day delivery with selectable time slots a critical challenge. This study introduces a novel Transformer-based approach enhanced with attention mechanisms to optimize time slot offerings and delivery routing dynamically. To the best of our knowledge, Transformers have not yet been applied to time slot management. Our model integrates real-time customer demand and operational constraints to minimize transportation costs, maximize vehicle capacity utilization, and maintain high service levels. We structure the problem into two interconnected phases: (1) dynamically generating personalized time slot menus based on customer arrivals and (2) optimizing vehicle dispatching and routing while adhering to selected time windows. To solve the Vehicle Dispatching Problem (VDP) and the Vehicle Routing Problem with Time Windows (VRP-TW), we employ a Hybrid Genetic Search heuristic and a Maximum Delay Time heuristic, ensuring cost-efficient routing and timely dispatching. Our approach provides effective and fast solutions for balancing customer satisfaction with operational efficiency in last-mile logistics.

Keywords

Status: accepted

Back to the list of papers