The objective of this paper is to examine the behavioural characteristics and patterns of pedestrians and vehicles in the context of emergency evacuation of car parks. Firstly, survey data is utilised to investigate the decision-making preferences of car park insiders in emergency evacuation scenarios. Secondly, the evacuation behaviours of pedestrians and vehicles are modelled using the XGBoost-SHAP model, with the objective of analysing the behavioural mechanisms in emergency evacuation situations. The results indicate that the density and distance of pedestrian exits are the primary factors influencing pedestrian choice. Furthermore, pedestrians with experience in emergency evacuation are more likely to select vehicle exits during emergency situations. With regard to vehicle choice, exit density was identified as the most significant influencing factor. In contrast, personal income and the presence of training were found to have a greater effect than exit distance. Concurrently, the selection of pedestrian and vehicle exits was influenced by a complex interaction of multiple factors.
Interpretable XGBoost-SHAP model for investigating car park pedestrian and vehicle emergency evacuation mechanisms
International Conference on Smart Transportation and City Engineering (STCE 2024) ; 2024 ; Chongqing, China
Proc. SPIE ; 13575
2025-04-28
Conference paper
Electronic Resource
English
An Optimization Model for Guiding Pedestrian–Vehicle Mixed Flows During an Emergency Evacuation
Taylor & Francis Verlag | 2014
|European Patent Office | 2025
|Extended Pedestrian Evacuation Model Considering Multiple Evacuation Behaviors
Transportation Research Record | 2025
|