Long, Yanyu (Coventry university), Sindi, Safaa (Coventry University), Birrell, Stewart (Coventry University), Loke, Seng (Deakin University), Nakisa, Bahareh (Deakin University)

Last-Mile Delivery Optimisation with Autonomous Vehicles and Drones for Trust-Aware Multimodal Medical Logistics in Urban Environments

Scheduled for presentation during the Regular Session "S45a-Decision-Making for Urban Air Mobility and Autonomous Logistics" (FR-LM-T45), Friday, November 21, 2025, 10:50−11:10, Gold Coast

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

This study addresses last-mile urban medical logistics through a multimodal fleet of autonomous vehicles and drones, including autonomous vans and trucks. We propose an environment-aware optimisation framework for last-mile delivery optimisation that integrates trust quantification, adaptive algorithm selection, and real-time decision making. The system models road and environmental conditions using multi source data and selects path-planning strategies, such as Dijkstra, A* or Greedy Best-First Search, according to delivery urgency and context. A trust evaluation mechanism fuses subjective perceptions with objective performance to embed trust scores into the optimisation process. Machine learning models predict delivery delays and guide vehicle scheduling under dynamic urban logistics network conditions. In simulations based on Coventry, UK; integrating trust metrics with environment-sensitive routing reduces mean delivery time by 28 %, while the delay-prediction error drops to ±3.04 s; drones deliver insulin 90 % faster than trucks despite slightly lower trust scores (-1.6 %). These findings underscore the value of incorporating socio-technical factors, especially trust, into time-sensitive, safety-critical multimodal urban logistics.