Wang, Xiaohan (The University of Hong Kong), Zhao, Zhan (The University of Hong Kong), Zhao, Luyun (The University of Hong Kong), Wu, liupengfei (The University of Hong Kong)

Just-In-Time Deliveries: Managing Uncertain Target Arrival Times with Adaptive Routing

Scheduled for presentation during the Regular Session "S39c-Data-Driven Optimization in Intelligent Transportation Systems" (FR-LA-T39), Friday, November 21, 2025, 16:20−16:40, Coolangata 3

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

Just-in-time delivery is essential in long-haul fleet-based freight transportation, where arriving either too early or too late can result in significant operational costs. Real-world unloading operations are frequently subject to delays and unforeseen disruptions, introducing uncertainty in the availability of unloading facilities. This forces subsequent trucks to either cruise on the road or search for alternative parking locations, both of which pose substantial risks for large freight fleets due to the scarcity of truck parking spaces and the sparsity of truck-accessible road networks. This paper addresses the routing problem under such temporal uncertainty, which is often overlooked in conventional routing algorithms that assume fixed or pre-defined time windows. We propose the Most Punctual Path (MPP) algorithm, an adaptive routing framework that decomposes the path planning process into a sequence of segment-level optimizations, enabling the expected travel time to continuously align with the latest probabilistic estimates of the target arrival time at each step. To evaluate the performance, we conduct experiments on a real-world road network and a sparser network simulating truck-specific constraints. Results across 10 origin-destination pairs demonstrate that MPP significantly outperforms baseline algorithms in minimizing arrival time deviations in sparse environments where detour options are limited.