Hierarchical GNN-Based Multi-Agent Learning for Dynamic Queue-Jump Lane and Emergency Vehicle Corridor Formation

TL;DR

This paper introduces a hierarchical GNN-based multi-agent reinforcement learning framework that effectively coordinates connected vehicles to form emergency corridors, significantly reducing travel time and maintaining safety in dynamic traffic conditions.

Contribution

The paper presents a novel hierarchical GNN and reinforcement learning approach for emergency vehicle corridor formation, integrating global planning with trajectory control.

Findings

Reduces emergency vehicle travel time by 28.3% compared to baselines.

Achieves near-zero collision rate of 0.3%.

Maintains 81% of background traffic efficiency.

Abstract

Emergency vehicles require rapid passage through congested traffic, yet existing strategies fail to adapt to dynamic conditions. We propose a novel hierarchical graph neural network (GNN)-based multi-agent reinforcement learning framework to coordinate connected vehicles for emergency corridor formation. Our approach uses a high-level planner for global strategy and low-level controllers for trajectory execution, utilizing graph attention networks to scale with variable agent counts. Trained via Multi-Agent Proximal Policy Optimization (MAPPO), the system reduces emergency vehicle travel time by 28.3% compared to baselines and 44.6% compared to uncoordinated traffic in simulations. The design achieves near-zero collision rates (0.3%) while maintaining 81% of background traffic efficiency. Ablation and generalization studies confirm the framework's robustness across diverse scenarios. These results demonstrate the effectiveness of combining GNNs with hierarchical learning for intelligent transportation systems.