Assessment of Latent Pedestrian--Vehicle Interaction Risk Profiles at Midblock Crossing in VR

2026-03-17

AI Summary

This study addresses the safety risks arising from pedestrians’ misjudgment of intentions between autonomous vehicles (AVs) and human-driven vehicles (HDVs) in mixed traffic, a risk modulated by environmental context. Through immersive virtual reality experiments conducted in Toronto and Newcastle, the research integrates surrogate safety measures (SSMs) with latent profile analysis (LPA)—the first application of LPA to VR-based pedestrian–vehicle interaction modeling—to identify distinct interaction risk profiles ranging from high risk acceptance to extreme caution. Findings reveal a significant increase in high-urgency risk scenarios in Newcastle under fully AV conditions, a trend absent in Toronto, demonstrating that local traffic environments moderate how AVs influence pedestrian risk behavior. These results underscore the critical role of contextual factors in traffic safety assessments involving AVs.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Natural Language Processing: Safety and Robustness

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience

Abstract

Pedestrian safety at midblock crossings is a critical concern in mixed traffic environments where autonomous vehicles (AVs) and human-driven vehicles (HDVs) share the road. Pedestrians often infer intent from vehicle motion in AV encounters, making them vulnerable to small shifts in conflict margins. This study investigates whether virtual reality (VR) crossing sessions separate into distinct interaction risk profiles and whether AV-only sessions shift profile prevalence compared to HDV-only sessions. Using large-scale immersive VR experiments from Toronto, Canada, and Newcastle, England, we compute surrogate safety measures (SSMs) and apply latent profile analysis (LPA) to identify distinct pedestrian crossing stances, ranging from risk-accepting to highly cautious. Key findings show that Newcastle exhibits a higher prevalence of high-urgency risk profiles in AV-only sessions, indicating that AVs contribute to higher-risk encounters. In contrast, Toronto shows no significant difference between AV-only and HDV-only sessions, suggesting that contextual factors influence the impact of AVs on pedestrian safety.

Problem

• pedestrian safety
• autonomous vehicles
• midblock crossing
• latent risk profiles
• mixed traffic

Innovation

• virtual reality
• latent profile analysis
• surrogate safety measures
• autonomous vehicles
• pedestrian-vehicle interaction