Modeling the Pedestrian Flow Before Bottleneck Through Learning-Based Method

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

View graph of relations



Original languageEnglish
Number of pages13
Journal / PublicationIEEE Transactions on Intelligent Transportation Systems
Issue number7
Online published20 Mar 2023
Publication statusPublished - Jul 2023


This paper proposes a learning-based approach for modeling microscopic pedestrian movement behavior before bottleneck which contains two sub models – velocity direction model and velocity magnitude model. Datasets extracted from fifteen controlled experiments were trained through CART algorithm in this approach. Fifteen original scenarios are adopted to evaluate the performance of the proposed approach from both macroscopic and microscopic aspects. Simulation results show that the trajectories and density, velocity, flow vs. time curves and fundamental diagrams are basically consistent with those from corresponding experiments. Four evaluation metrics, final displacement error (FDE), duration error (DE), mean trajectory error (MTE) and relative distance error (RDE) are applied to quantitatively verify the precision of simulation. The mean of FDE, DE, and MTE are calculated to be 0.144 m, 0.112 s and 0.095 m respectively. With time intervals of 0.5 s, 1 s and 2 s, the mean RDE of all scenarios are respectively 0.7089, 0.4073 and 0.2515. Data from additional experiments of bottleneck scenarios and publicly available data of corridor scenarios are also introduced to prove the potential of general application of this approach. Comparisons and analysis indicate that the proposed approach has a good capability and reliability in simulating the pedestrian motion before the bottleneck. The models presented will be useful for passenger flow management and architectural design, also beneficial to understand the pedestrian movement mechanism in collective motion. © 2023 IEEE.

Research Area(s)

  • Behavioral sciences, bottleneck, Computational modeling, Force, machine learning, Microscopy, Neural networks, Pedestrian flow, Predictive models, Trajectory, walking behavior