Modelling Pedestrian Behaviour in Autonomous Vehicle Encounters Using Naturalistic Dataset

2026-02-04

AI Summary

This study addresses safety in mixed traffic by modeling microscopic behavioral adjustments during interactions between pedestrians and autonomous vehicles. Leveraging the NuScenes naturalistic driving dataset, the authors propose a Residual Logit (ResLogit) model that integrates discrete choice modeling with machine learning to incorporate multidimensional perceptual and kinematic features—including spatiotemporal characteristics, visual looming, relative velocity, time-to-collision, and a newly introduced directional Collision Risk Proximity (CRP) metric. The analysis reveals an asymmetry in pedestrian risk perception between front and rear approaches and identifies a threshold effect associated with mid-crossing behavior. Although the model exhibits moderate predictive performance, it demonstrates strong interpretability of behavioral mechanisms, offering a novel perspective on the decision-making processes underlying human–vehicle interactions.

Technology Category

• Natural Language Processing: Safety and Robustness
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Security and Privacy: Large-scale security measurements

Abstract

Understanding how pedestrians adjust their movement when interacting with autonomous vehicles (AVs) is essential for improving safety in mixed traffic. This study examines micro-level pedestrian behaviour during midblock encounters in the NuScenes dataset using a hybrid discrete choice-machine learning framework based on the Residual Logit (ResLogit) model. The model incorporates temporal, spatial, kinematic, and perceptual indicators. These include relative speed, visual looming, remaining distance, and directional collision risk proximity (CRP) measures. Results suggest that some of these variables may meaningfully influence movement adjustments, although predictive performance remains moderate. Marginal effects and elasticities indicate strong directional asymmetries in risk perception, with frontal and rear CRP showing opposite influences. The remaining distance exhibits a possible mid-crossing threshold. Relative speed cues appear to have a comparatively less effect. These patterns may reflect multiple behavioural tendencies driven by both risk perception and movement efficiency.

Problem

• pedestrian behaviour
• autonomous vehicles
• risk perception
• mixed traffic
• movement adjustment

Innovation

• Residual Logit model
• pedestrian behaviour
• autonomous vehicles
• collision risk proximity
• naturalistic dataset