Improving Work Zone Safety: Integrating VR-CARLA Co-simulation and Eye Tracking for Behavior Analysis of Drivers around Work Zones

Zhang, Shuo; Zuo, Fan; Ergan, Semiha; Ozbay, Kaan · 2025 · ROSA P / Connected Communities for Smart Mobility Toward Accessible and Resilient Transportation for Equitably Reducing Congestion (C2SMARTER) Tier-1 University Transportation Center (UTC)

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 addresses the persistent safety challenges in roadway work zones, where driver-worker interactions often lead to accidents despite existing safety measures. Motivated by the lack of comprehensive data on driver situational awareness and the limitations of real-world studies in replicating hazardous scenarios safely, the authors aim to understand how work zone configurations and worker behaviors influence driver attention. The research specifically investigates the impact of warning signs and risky worker behaviors on drivers' visual focus, seeking to inform better traffic control measures and work zone designs. To achieve this, the researchers developed an immersive driving simulation platform integrating Virtual Reality (VR), the CARLA traffic simulator, and eye-tracking technology. The system utilized a Logitech G29 racing wheel for vehicle control and Beam Eye Tracker glasses to record gaze metrics. Worker behaviors were simulated using full-body animations within the Unreal Engine, depicting either normal tasks (idling, squatting) or risky behaviors (idling outside the work zone boundary). The experimental design involved two scenarios: one without warning signs (S1) and one with warning signs at the work zone entrance (S2). Each scenario included three cases: an empty work zone (C1), a zone with two normally behaving workers (C2), and a zone with one normal worker and one exhibiting risky behavior (C3). Twenty licensed drivers participated in user studies, navigating these six scenario-case combinations while their gaze duration and fixation ratios were recorded. The findings reveal that drivers prioritize their visual attention on workers exhibiting risky behaviors over warning signs or normally behaving workers. Gaze fixation ratios for risky workers were consistently higher than for normal workers across both scenarios, indicating that hazardous conditions disproportionately divert driver attention. While the presence of warning signs reduced variability in gaze duration and enhanced awareness of normal workers in safe conditions, it did not significantly alter attention toward risky workers. Statistical analysis using paired t-tests confirmed that drivers paid significantly more attention to normal workers when warning signs were present in hazardous contexts (S2C3 vs. S1C3), but attention to risky workers remained high regardless of signage. Additionally, the absence of warning signs increased driver uncertainty, leading to longer gaze durations and greater variability in attention. The study concludes that current warning signage is insufficient to mitigate the distraction caused by risky worker behaviors. Drivers naturally focus on perceived hazards, such as workers outside designated zones, often at the expense of monitoring other elements. The authors recommend implementing multi-type notification systems, including dynamic digital displays, wearable devices for workers, and auditory alerts, to maintain comprehensive driver awareness. These findings highlight the need for adaptive work zone designs that account for driver variability and the specific attention-grabbing nature of risky behaviors, offering a data-driven approach to enhancing safety through improved situational awareness strategies.

Key finding

Drivers disproportionately allocate visual attention to workers exhibiting risky behaviors compared to warning signs and normal workers, a pattern that persists regardless of the presence of warning signs.

Methodology

simulator

Sample size: 20

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.

• work zones
• gaze based attention detection
• emergency work zone conspicuity
• visual
• attention allocation
• eye movements scanning

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: behavioral performance data
• Methodological Resource: tool software
• Theoretical Contribution: theory or model