Questioning the Anisotropy of Pedestrian Dynamics: An Empirical Analysis with Artificial Neural Networks

Abstract

Identifying the factors that control the dynamics of pedestrians is a crucial step towards modeling and building various pedestrian-oriented simulation systems. In this article, we empirically explore the influential factors that control the single-file movement of pedestrians and their impact. Our goal in this context is to apply feed-forward neural networks to predict and understand the individual speeds for different densities of pedestrians. With artificial neural networks, we can approximate the fitting function that describes pedestrians’ movement without having modeling bias. Our analysis is focused on the distances and range of interactions across neighboring pedestrians. As indicated by previous research, we find that the speed of pedestrians depends on the distance to the predecessor. Yet, in contrast to classical purely anisotropic approaches—which are based on vision fields and assume that the interaction mainly depends on the distance in front—our results demonstrate that the distance to the follower also significantly influences movement. Using the distance to the follower combined with the subject pedestrian’s headway distance to predict the speed improves the estimation by 18% compared to the prediction using the space in front alone.

Influence of Gender Composition in Pedestrian Single-File Experiments

“…When we look more closely into the specific structure, it becomes clear that there are also variations depending on the experimental setup. The type of flow, such as uni-, bi-, or multidirectional streams; human factors such as age, gender, height, and culture [3,[18][19][20][21][22][23][24][25][26], or external factors such as restricted visibility [27], different height adjustments due to smoke [28], motivation or instruction [18], temperature [29], sidewalk quality [29,30], rhythm or background music [31,32], or properties of human movement, such as step length and frequency [33][34][35][36][37][38][39], all affect the fundamental diagram. This list is only exemplary and does not claim to be complete.…”

“…However, a comparison with data from other cultures and different ages raises the question of which other factors also need to be considered. In [21], using the data from the experiments introduced in [20], Subaih et al have shown that the headway to the front and to the back is important, too. This result suggests that the arrangement by gender has an effect on the distances between pedestrians and must be taken into account in modeling the speed-density relation.…”

“…To analyze these contradictory findings, further single-file experiments are performed for the present study. Four different group compositions, female, male, gender alternating, and gender random order, are considered to investigate the following three hypotheses derived from the studies to date [20,21,40].…”