Predicting and Analyzing Pedestrian Crossing Behavior at Unsignalized Crossings

TL;DR

This work investigates pedestrian crossing behavior at unsignalized crossings using VR-simulated data with multi-vehicle interactions to predict two tasks: (1) pedestrian gap selection for crossing non-zebra roads and (2) zebra-crossing usage. It compares linear, random forest, and neural network models, revealing neural networks as the strongest predictor with a mean absolute error around $1.07$ seconds for gap prediction and accuracy around $94\%$ for zebra usage. The study identifies key predictors, including waiting time $T_w$, walking speed $v_p$, counts and sizes of missed gaps ($N_{en},N_{ef},N_{cb},M_{en},M_{ef},M_{eb}$), and group-following dynamics, and connects results to the critical gap concept $\text{Gap}=\frac{L}{S}+F$. Findings offer actionable insights for intelligent vehicles to anticipate pedestrian decisions and adjust speed/trajectories, while acknowledging limitations such as cultural specificity and uncertainties in gap durations.

Abstract

Understanding and predicting pedestrian crossing behavior is essential for enhancing automated driving and improving driving safety. Predicting gap selection behavior and the use of zebra crossing enables driving systems to proactively respond and prevent potential conflicts. This task is particularly challenging at unsignalized crossings due to the ambiguous right of way, requiring pedestrians to constantly interact with vehicles and other pedestrians. This study addresses these challenges by utilizing simulator data to investigate scenarios involving multiple vehicles and pedestrians. We propose and evaluate machine learning models to predict gap selection in non-zebra scenarios and zebra crossing usage in zebra scenarios. We investigate and discuss how pedestrians' behaviors are influenced by various factors, including pedestrian waiting time, walking speed, the number of unused gaps, the largest missed gap, and the influence of other pedestrians. This research contributes to the evolution of intelligent vehicles by providing predictive models and valuable insights into pedestrian crossing behavior.

Figures (10)

• Figure 1: Schematic overview of the experimental environment. Start (yellow) and goal (green) are visualized and alternated between north and south sides of the road in every other trial. Cars were approaching from both directions with randomly selected gaps per lane.
• Figure 2: The boxplots of the predicted accepted gaps for different models. GT for ground truth, LR for linear regression, RF for random forest, and NN for neural network.
• Figure 3: The mean value of the accepted gap versus the number of unused car gaps for both lanes. Pedestrians tend to accept smaller gaps for crossing as the number of unused car gaps increases.
• Figure 4: The mean value of the accepted gap versus the largest missed car gap for both lanes. Pedestrians tend to accept smaller gaps for crossing as the largest missed gap increases.
• Figure 5: The mean value of the accepted gap versus pedestrian waiting time. Pedestrians tend to select larger gaps when the waiting time increases.