Predicting Pedestrian Crossing Behavior in Germany and Japan: Insights into Model Transferability

TL;DR

This study compares pedestrian crossing behaviors in Germany and Japan, evaluates machine learning models for prediction, and develops a transferable model that improves accuracy across countries, enhancing traffic safety systems.

Contribution

It introduces a transferable machine learning model for pedestrian crossing behavior prediction that accounts for cross-country differences using unsupervised clustering.

Findings

Japanese pedestrians are more cautious, selecting larger gaps.

Neural networks outperform other models in predicting crossing behaviors.

Random forests excel in trajectory prediction and transferability.

Abstract

Predicting pedestrian crossing behavior is important for intelligent traffic systems to avoid pedestrian-vehicle collisions. Most existing pedestrian crossing behavior models are trained and evaluated on datasets collected from a single country, overlooking differences between countries. To address this gap, we compared pedestrian road-crossing behavior at unsignalized crossings in Germany and Japan. We presented four types of machine learning models to predict gap selection behavior, zebra crossing usage, and their trajectories using simulator data collected from both countries. When comparing the differences between countries, pedestrians from the study conducted in Japan are more cautious, selecting larger gaps compared to those in Germany. We evaluate and analyze model transferability. Our results show that neural networks outperform other machine learning models in predicting gap selection and zebra crossing usage, while random forest models perform best on trajectory prediction tasks, demonstrating strong performance and transferability. We develop a transferable model using an unsupervised clustering method, which improves prediction accuracy for gap selection and trajectory prediction. These findings provide a deeper understanding of pedestrian crossing behaviors in different countries and offer valuable insights into model transferability.