Hybrid Machine Learning and Physics-based Modelling of Pedestrian Pushing Behaviours at Bottlenecks

TL;DR

This paper develops a hybrid model combining machine learning and physics-based approaches to predict and simulate pedestrian pushing behaviors at bottlenecks, addressing data scarcity and heterogeneity.

Contribution

It introduces a novel hybrid modeling framework that integrates pushing tendencies, behavior prediction, and movement strategies for more accurate crowd dynamics simulation.

Findings

The model accurately reproduces experimental crowd behaviors.

Pushing behaviors are linked to aggressive space utilization.

The approach effectively incorporates pedestrian heterogeneity.

Abstract

In high-density crowds, close proximity between pedestrians makes the steady state highly vulnerable to disruption by pushing behaviours, potentially leading to serious accidents. However, the scarcity of experimental data has hindered systematic studies of its mechanisms and accurate modelling. Using behavioural data from bottleneck experiments, we investigate pedestrian heterogeneity in pushing tendencies, showing that pedestrians tend to push under high-motivation and in wider corridors. We introduce a spatial discretization method to encode neighbour states into feature vectors, serving together with pedestrian pushing tendencies as inputs to a random forest model for predicting pushing behaviours. Through comparing speed-headway relationships, we reveal that pushing behaviours correspond to an aggressive space-utilization movement strategy. Consequently, we propose a hybrid machine learning and physics-based model integrating pushing tendencies heterogeneity, pushing behaviours prediction, and dynamic movement strategies adjustment. Validations show that the hybrid model effectively reproduces experimental crowd dynamics and fits to incorporate additional behaviours.