AI-Driven Vehicle Route Optimization Using GNN and Multi-Agent Reinforcement Learning

Himanshu Seth

doi:10.71097/IJSAT.v17.i2.11320

AI-Driven Vehicle Route Optimization Using GNN and Multi-Agent Reinforcement Learning

Author(s)	Himanshu Seth
Country	United States
Abstract	The Vehicle Routing Problem (VRP) is a fundamental challenge in intelligent transportation systems due to its NP-hard complexity and sensitivity to dynamic, real-world constraints. The rapid expansion of e-commerce, urban congestion, and sustainability requirements has rendered traditional routing approaches inadequate, as they rely on static heuristics and lack adaptability to time-varying environments. In this paper, we propose a novel Graph-Enhanced Multi-Agent Reinforcement Learning (GEMARL) framework for dynamic vehicle route optimization in heterogeneous logistics networks. The proposed approach integrates graph neural networks (GNNs) to model spatiotemporal dependencies in transportation graphs with decentralized multi-agent reinforcement learning (MARL) to enable scalable, real-time decision making. The routing problem is formulated as a constrained multi-objective optimization task that jointly minimizes delivery time, operational cost, and carbon emissions under capacity, time-window, and energy constraints. The effectiveness of the proposed framework is validated through four representative case studies, including last-mile truck-drone delivery, urban electric vehicle (EV) logistics, multi-echelon supply chain coordination, and drone fleet management. Extensive experimental evaluations demonstrate that GEMARL achieves up to 30% reduction in delivery time, 25% improvement in energy efficiency, and 40% reduction in emissions compared to conventional optimization techniques and state-of-the-art learning-based methods. These results highlight the potential of hybrid AI-driven approaches to enable scalable, adaptive, and sustainability-aware logistics systems. Future research directions include quantum-enhanced optimization and integration with smart city infrastructures.
Keywords	Vehicle routing problem (VRP), intelligent transportation systems (ITS), graph neural networks (GNNs), multi-agent reinforcement learning (MARL), dynamic routing, multi-objective optimization, smart logistics, heterogeneous fleets, sustainable transportation, drone delivery, electric vehicles, quantum optimization.
Field	Engineering
Published In	Volume 17, Issue 2, April-June 2026
Published On	2026-06-06
DOI	https://doi.org/10.71097/IJSAT.v17.i2.11320

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 17 Isu 2 Cover Page Vol 17 Isu 1 Cover Page Vol 16 Isu 4

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

AI-Driven Vehicle Route Optimization Using GNN and Multi-Agent Reinforcement Learning

Share this