What does this research mean for the field?

A multi-modal evacuation framework utilizing Uncertainty-Aware Reinforcement Learning to coordinate diverted in-service buses and dedicated shuttles reduces evacuation completion time by 31.6% and passenger waiting time by 48.4% compared to shuttle-only strategies. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To develop a multi-modal collaborative evacuation framework coordinating diverted in-service buses and pre-positioned shuttles under travel time uncertainty during large-scale public events.

September 14, 2026Systems0 citationsOpen Access

Multi-Modal Collaborative Evacuation During Mass Gatherings Using Distributional Reinforcement...

Multi-Modal Collaborative Evacuation During Mass Gatherings via Distributional Reinforcement Learning

View Full Paper

Ask AI

Bookmark

Authors

WWWensi Wang XXXiangsen Xu LHLiangmu Hou

Discussion

Member takes

Overview

Simulation study demonstrates accelerated crowd clearing and reduced wait times during mass gatherings, suggesting enhanced resilience through multi-modal reinforcement learning.

Key Points

To develop a multi-modal collaborative evacuation framework coordinating diverted in-service buses and pre-positioned shuttles under travel time uncertainty during large-scale public events.
Formulated a two-layer stochastic optimization model where the upper layer determines pre-event shuttle fleet sizing and the lower layer governs real-time dispatching.
Developed an Uncertainty-Aware Reinforcement Learning framework with Categorical DQN (UARL-CD) integrating distributional value representations, stochastic training, and action masking.
Tested performance through simulation experiments modeling a realistic stadium evacuation scenario against deterministic optimization and rule-based heuristics.
Achieved a 31.6% reduction in evacuation completion time and a 48.4% reduction in average passenger waiting time compared to using shuttles alone.
Preserved operational robustness under travel time uncertainty with only 4.0% performance degradation.
Generated online dispatching decisions within the required 2-minute decision interval.

Cite This Study

Wang et al. (2026) studied this question.

synapsesocial.com/papers/6aa7b2c70926e14a848b14e3 https://doi.org/10.3390/systems14091135

View Full Paper

Ask AI

Bookmark

September 14, 2026Systems0 citationsOpen Access

Multi-Modal Collaborative Evacuation During Mass Gatherings Using Distributional Reinforcement...

Multi-Modal Collaborative Evacuation During Mass Gatherings via Distributional Reinforcement Learning

View Full Paper

Ask AI

Bookmark

Authors

WWWensi Wang XXXiangsen Xu LHLiangmu Hou

Discussion

Member takes

Overview

Simulation study demonstrates accelerated crowd clearing and reduced wait times during mass gatherings, suggesting enhanced resilience through multi-modal reinforcement learning.

Key Points

To develop a multi-modal collaborative evacuation framework coordinating diverted in-service buses and pre-positioned shuttles under travel time uncertainty during large-scale public events.
Formulated a two-layer stochastic optimization model where the upper layer determines pre-event shuttle fleet sizing and the lower layer governs real-time dispatching.
Developed an Uncertainty-Aware Reinforcement Learning framework with Categorical DQN (UARL-CD) integrating distributional value representations, stochastic training, and action masking.
Tested performance through simulation experiments modeling a realistic stadium evacuation scenario against deterministic optimization and rule-based heuristics.
Achieved a 31.6% reduction in evacuation completion time and a 48.4% reduction in average passenger waiting time compared to using shuttles alone.
Preserved operational robustness under travel time uncertainty with only 4.0% performance degradation.
Generated online dispatching decisions within the required 2-minute decision interval.

Cite This Study

Wang et al. (2026) studied this question.

synapsesocial.com/papers/6aa7b2c70926e14a848b14e3 https://doi.org/10.3390/systems14091135

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark