![[2602.14676] GREAT-EER: Graph Edge Attention Network for Emergency Evacuation Responses](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.14676] GREAT-EER: Graph Edge Attention Network for Emergency Evacuation Responses
Summary
The paper presents GREAT-EER, a Graph Edge Attention Network designed to optimize emergency evacuation responses by solving the Bus Evacuation Orienteering Problem (BEOP) using deep reinforcement learning.
Why It Matters
As urban areas face increasing threats from natural and man-made disasters, efficient evacuation strategies are crucial. This research offers a novel approach to enhance evacuation planning, potentially saving lives and improving response times during emergencies.
Key Takeaways
- Introduces the Bus Evacuation Orienteering Problem (BEOP) as a critical challenge in emergency management.
- Proposes a deep reinforcement learning method that utilizes graph learning for rapid evacuation route planning.
- Demonstrates near-optimal solution quality through real-world scenario testing in San Francisco.
- Highlights the importance of bus-based evacuations to alleviate congestion in disaster scenarios.
- Establishes a framework for determining the number of evacuation vehicles needed based on predefined quotas.
Computer Science > Artificial Intelligence arXiv:2602.14676 (cs) [Submitted on 16 Feb 2026] Title:GREAT-EER: Graph Edge Attention Network for Emergency Evacuation Responses Authors:Attila Lischka, Balázs Kulcsár View a PDF of the paper titled GREAT-EER: Graph Edge Attention Network for Emergency Evacuation Responses, by Attila Lischka and Bal\'azs Kulcs\'ar View PDF HTML (experimental) 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. W...
