Truck Driver Fatigue Assessment Using a Virtual Reality System

Ali, Ayman; Mehta, Yusuf · 2016 · ROSA P / City University of New York. University Transportation Research 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 addresses the critical safety issue of truck driver fatigue, a significant contributor to fatal traffic crashes. While existing regulations like Hour-of-Service rules mitigate risk, there is a need for technological solutions to characterize fatigue in real-time. Previous research has utilized driving simulators to assess fatigue, but these often lack full immersion and the ability to simulate varying environmental conditions such as weather and time of day. This paper presents a proof-of-concept study demonstrating that a fully immersive Virtual Reality (VR) driving simulator can effectively assess driver fatigue levels and evaluate the impact of varying driving conditions. The researchers developed a VR-based truck driving simulator using Unity software and modified gaming hardware, including a seat and steering wheel adapted to mimic a semi-trailer truck. The simulation environment replicated a route from Washington, D.C., to New York City, incorporating realistic physics, lane markings, and variable weather conditions (clear, rainy, foggy) and times of day (day, night). Four drivers participated in the study: two classified as fatigued (tested after eight hours of work) and two as unfatigued (tested in the morning). Each driver completed a two-hour simulation with conditions changing every 15 minutes. Two specific fatigue metrics were measured: "sway ratio," calculated by analyzing the truck’s lateral position relative to a defined non-sway zone, and "reaction time," measured by the driver’s response to a visual stimulus on the screen. Data was analyzed using multi-factor statistical analysis (ANOVA). The results indicated that VR-based simulators are a viable alternative to traditional simulators for assessing driver drowsiness. Both sway ratio and reaction time successfully distinguished between fatigued and unfatigued drivers, with fatigued drivers exhibiting higher sway ratios and slower reaction times. The study further found that weather conditions influenced fatigue measures; specifically, the sway ratio was significantly affected by rainy conditions. The statistical analysis confirmed that these metrics could clearly differentiate between the two driver groups, validating the simulator’s capability to capture fatigue-related behavioral changes. The significance of this work lies in establishing VR technology as a cost-effective and realistic tool for developing and testing fatigue detection systems. By demonstrating that VR can replicate real-life driving stresses and environmental variables, the study supports the advancement of immersive simulation in transportation research. The findings suggest that sway ratio and reaction time are robust metrics for characterizing fatigue, offering potential pathways for integrating these measures into future in-vehicle safety technologies. This approach allows for safer, more controlled evaluation of driver states compared to real-world testing, while providing greater environmental fidelity than traditional static simulators.

Key finding

Sway ratio and reaction time measures successfully distinguished between fatigued and unfatigued drivers, confirming the viability of VR-based simulators for fatigue assessment.

Methodology

simulator

Sample size: 4

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.

• truck driver fatigue
• drowsiness detection algorithms
• simulator validity fidelity
• workload measurement

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: physiological data
• Methodological Resource: tool software, validation psychometrics