GREAT-EER: Graph Edge Attention Network for Emergency Evacuation Responses

2026-02-16

AI Summary

This study addresses the bus evacuation orienteering problem (BEOP)—the challenge of maximizing public transit evacuation efficiency within a limited time during urban emergencies. The authors propose a novel approach that integrates graph neural networks with deep reinforcement learning, introducing an edge-wise graph attention mechanism for path planning that generates near-optimal evacuation plans in milliseconds. To provide theoretical performance bounds, the method is complemented by mixed-integer linear programming (MILP) formulations. Experiments on San Francisco’s real-world road network demonstrate that the proposed framework significantly improves evacuation efficiency, effectively reduces traffic congestion, and quantifies the maximum number of evacuees achievable under varying levels of bus resource availability.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Combinatorial Optimization
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Emergency situations that require the evacuation of urban areas can arise from man-made causes (e.g., terrorist attacks or industrial accidents) or natural disasters, the latter becoming more frequent due to climate change. As a result, effective and fast methods to develop evacuation plans are of great importance. In this work, we identify and propose the Bus Evacuation Orienteering Problem (BEOP), an NP-hard combinatorial optimization problem with the goal of evacuating as many people from an affected area by bus in a short, predefined amount of time. The purpose of bus-based evacuation is to reduce congestion and disorder that arises in purely car-focused evacuation scenarios. To solve the BEOP, we propose a deep reinforcement learning-based method utilizing graph learning, which, once trained, achieves fast inference speed and is able to create evacuation routes in fractions of seconds. We can bound the gap of our evacuation plans using an MILP formulation. To validate our method, we create evacuation scenarios for San Francisco using real-world road networks and travel times. We show that we achieve near-optimal solution quality and are further able to investigate how many evacuation vehicles are necessary to achieve certain bus-based evacuation quotas given a predefined evacuation time while keeping run time adequate.

Problem

• Emergency Evacuation
• Bus Evacuation Orienteering Problem
• Urban Evacuation
• Combinatorial Optimization
• Evacuation Planning

Innovation

• Graph Edge Attention Network
• Bus Evacuation Orienteering Problem
• Deep Reinforcement Learning
• Emergency Evacuation Planning
• Combinatorial Optimization