Routing Diverse Crowds in Emergency with Dynamic Grouping

TL;DR

This paper introduces a QoS-driven multi-path routing algorithm for emergency evacuation that dynamically groups evacuees based on their conditions, improving safety and adaptability in hazardous environments.

Contribution

It presents a novel dynamic grouping and routing algorithm inspired by Cognitive Packet Network principles, tailored for diverse evacuee needs during emergencies.

Findings

Better evacuation outcomes with multiple routing metrics.

Dynamic grouping improves adaptability to hazard changes.

Higher survival rates with the proposed method.

Abstract

Evacuee routing algorithms in emergency typically adopt one single criterion to compute desired paths and ignore the specific requirements of users caused by different physical strength, mobility and level of resistance to hazard. In this paper, we present a quality of service (QoS) driven multi-path routing algorithm to provide diverse paths for different categories of evacuees. This algorithm borrows the concept of Cognitive Packet Network (CPN), which is a flexible protocol that can rapidly solve optimal solution for any user-defined goal function. Spatial information regarding the location and spread of hazards is taken into consideration to avoid that evacuees be directed towards hazardous zones. Furthermore, since previous emergency navigation algorithms are normally insensitive to sudden changes in the hazard environment such as abrupt congestion or injury of civilians, evacuees are dynamically assigned to several groups to adapt their course of action with regard to their on-going physical condition and environments. Simulation results indicate that the proposed algorithm which is sensitive to the needs of evacuees produces better results than the use of a single metric. Simulations also show that the use of dynamic grouping to adjust the evacuees' category and routing algorithms with regard for their on-going health conditions and mobility, can achieve higher survival rates.