Predictive Agent-Based Crowd Model Design Using Decentralized Control Systems

Abstract

As a complex system, crowd dynamics emerge bottom-up from the local interactions between pedestrians as component subsystems. This article proposes a predictive agent-based crowd simulation model to analyze the outcomes of emergency evacuation scenarios taking into account collisions between pedestrians, smoke, fire sprinklers, and exit indicators. The crowd model is based on a decentralized control system structure, where each pedestrian agent is governed through a deliberative-reactive control architecture. The simulation model for evacuation includes a routing-based control system for dynamic-guided evacuation. A design case illustrates the modeling process. Results show that the crowd simulation model based on agent autonomy and local interactions is able to generate higher level crowd dynamics through emergence.

Help Me Evacuate! A Smart Adaptable Evacuation System With Congestion Prediction Capabilities

“…As for smart evacuation guidance systems, they are relatively novel in research; however, the number of research studies has significantly increased in the past few years. Most existing research works employ Internet of Things (IoT) [32,34,37,39,41,42]. Then, this data is used to assess emergencies, develop a suitable evacuation plan, and display rerouting updates via dynamic signage systems.…”

“…Also, Xu et al [41] add a parameter to the route selection probability of ant colony algorithm, which takes fire conditions into consideration to penalize hazardous paths and avoid them. Additionally, Berceanu et al [42] propose a decentralized agent-based model that uses a guidance control system, which weights paths according to fire conditions to compute the shortest and safest paths using Dijkstra's algorithm. However, such strategies turn out to be a greedy shortest-path strategy after making hazardous areas inaccessible.…”

A Spatio-Temporal Cognitive Framework for Individual Route Choice in Outdoor Evacuation Scenarios

“…Mental frameworks are designed from cognitive neuroscience and psychobehavioral science concerning the internal representation of the external environment in the human mind. In these mental frameworks, individuals are generally treated as agents who continuously perceive external environmental stimuli, form cognition knowledge, and perform physical actions [18,19]. The cognitive map is one of the most typical works of these cognitive mental frameworks.…”