Augmented Reality for Safer Pedestrian-Vehicle Interactions

Noyce, David A.; Nassereddine, Hiba; Santiago-Chaparro, Kelvin R. · 2018 · ROSA P / Safety Research Using Simulation (SAFER-SIM) University Transportation Center

archive: archived pipeline: cataloged verified

Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)

Summary

This study investigates whether augmented reality (AR) advanced warning messages can improve driver detection of pedestrians and bicyclists, particularly in scenarios where these vulnerable road users are unexpected or have low visibility. The research is motivated by the high prevalence of driver error in crashes and the potential for AR technology to supplement driver perception by providing early alerts about hazards that are not yet visible or are difficult to detect. The primary objective was to determine if auditory and visual cues, triggered significantly ahead of a pedestrian or bicyclist, could enhance recognition and safety. The researchers conducted an experiment using a full-scale driving simulator at the University of Wisconsin–Madison. Participants were exposed to specific scenarios involving pedestrians and bicyclists on both rural and urban roadways. The experimental design compared driver performance in control conditions (no alert) against treatment conditions where AR warnings were displayed. These warnings included visual cues, such as highlighted bounding boxes or signs, and auditory alerts. Data collection focused on the location of detection events, measuring the distance at which drivers identified the vulnerable road user, as well as vehicle speed profiles to assess braking behavior and reaction times. Statistical analyses, including Kruskal-Wallis and Wilcoxon tests, were employed to evaluate the significance of differences between control and treatment groups across various events and environmental categories. The results indicated that AR cues significantly impacted driver behavior. In distance-based analyses, drivers in the treatment groups detected pedestrians and bicyclists earlier than those in the control groups, particularly in rural environments where pedestrians are less expected. The data showed that the presence of advanced warnings reduced the distance to detection, allowing drivers more time to react. Speed-based analyses revealed that drivers receiving AR alerts tended to decelerate earlier and more gradually compared to those without alerts, who often braked more urgently upon visual detection. The study found that AR cues helped drivers anticipate potential crossings, leading to smoother speed adjustments and improved situational awareness without increasing cognitive workload or distraction. The findings suggest that AR technology holds significant promise for enhancing pedestrian-vehicle safety by addressing recognition errors, which are a leading cause of crashes. By providing drivers with advanced knowledge of hazards, AR systems can compensate for human perceptual limitations and low-visibility conditions. The study concludes that integrating such warnings into connected vehicle systems could reduce pedestrian injuries and fatalities, especially in rural areas or unexpected crossing scenarios. The research supports the development of in-vehicle AR displays as a viable safety intervention, highlighting the need for further work to optimize cue design and integration with emerging connected vehicle infrastructure.

Key finding

Drivers detected pedestrians and bicyclists at significantly greater distances and demonstrated more proactive speed reduction when augmented reality warning cues were provided compared to no-alert conditions.

Methodology

simulator

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• hud ar windshield
• vru facing ehmi
• ehmi external hmi
• vru conspicuity
• pedestrian behavior perception
• external distraction

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Empirical Findings: observational prevalence
• Methodological Resource: tool software