Wait or cross? Understanding the influence of behavioral tendency, trust, and risk perception on pedestrian gap-acceptance of automated truck platoons

2026-01-06

arXiv.org

AI Summary

This study investigates pedestrians’ crossing decisions when encountering platoons of autonomous trucks, with a focus on how behavioral propensity, trust, and risk perception influence gap acceptance behavior. Drawing on data from 603 participants in a virtual reality video-based questionnaire experiment, the authors develop a two-stage hybrid model integrating structural equation modeling and artificial neural networks. The approach innovatively combines latent variable modeling with nonlinear prediction to uncover the mediating role of risk perception in the relationship between behavioral propensity, trust, and crossing decisions. Results indicate that pedestrians typically observe an average of five vehicle gaps before crossing, accepting a mean time gap of 5.35 seconds. Risk perception emerges as the dominant factor in decision-making: violators tend to accept smaller gaps, while individuals with higher trust levels exhibit significantly lower perceived risk.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Application Domains: Transportation
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

Although automated trucks have the potential to improve freight efficiency, reduce costs, and address driver shortages, organizing two or more trucks in a convoy has raised considerable concerns for pedestrian safety. This study conducted a controlled experiment to examine the influence of behavioral tendency, trust, and risk perception on pedestrian intention to cross in front of an automated truck platoon. A total of 603 subjects participated in the virtual reality video-based questionnaire survey. By fusing the merits of structural equation modeling and artificial neural networks, a two-stage, hybrid model was developed to examine complex relationships between latent variables and gap-acceptance behaviors. Our results indicated that subjects watched an average of five vehicle gaps before starting crossing and the average time gap accepted was about 5.35 seconds. Risk perception not only played the most dominant role in shaping pedestrian crossing decisions, but also served as the strong bone, mediating the effects of behavioral tendency and trust on gap-acceptance. Participants who frequently violated traffic rules were more likely to accept a smaller time gap, while those who showed positive behaviors to other road users tended to wait for a larger time gap. Participants who often committed errors, showed aggressive behaviors, and held greater trust in the safety of automated trucks generally reported a lower level of risk for road-crossing in front of automated truck platoons. Built on these findings, a range of tailored countermeasures were proposed to ensure safer and smother interactions between pedestrians and automated truck platoons.

Problem

• pedestrian gap-acceptance
• automated truck platoons
• risk perception
• behavioral tendency
• trust

Innovation

• hybrid SEM-ANN model
• gap-acceptance behavior
• risk perception
• automated truck platoons
• virtual reality experiment