Analysis of Naturalistic Driving Data to Assess Distraction and Drowsiness in Drivers of Commercial Motor Vehicles

Hammond, Rebecca L.; Soccolich, Susan A.; Guo, Feng; Glenn, T. Laurel; Hanowski, Richard J.; Han, Shu · 2021 · ROSA P / United States. Department of Transportation. Federal Motor Carrier Safety Administration. Office of Analysis, Research, and Technology

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, conducted by the Virginia Tech Transportation Institute for the Federal Motor Carrier Safety Administration (FMCSA), analyzes naturalistic driving data to assess the roles of distraction and drowsiness in crashes involving commercial motor vehicles (CMVs). The research aims to support FMCSA’s mission to reduce crashes, injuries, and fatalities by providing empirical evidence on driver behavior in heavy trucks and motorcoaches. The study specifically investigates the prevalence and risk associated with secondary tasks, such as cell phone use, and examines how fatigue varies with driving duration, offering insights relevant to hours-of-service regulations. The analysis utilized over 3.8 million miles of data collected from 225 vehicles and 245 drivers across seven fleets and ten locations, sourced from the Onboard Monitoring System Field Operational Test. The dataset included 43 motorcoaches with 73 drivers and 182 trucks with 172 drivers. Researchers employed a rigorous data reduction process, identifying Safety Critical Events (SCEs) and baseline driving epochs. They calculated Odds Ratios (ORs) and Population Attributable Risk (PAR) to quantify the risk associated with specific behaviors. Drowsiness was measured using the Objective Rating of Driver State (ORD) and manual Percentage of Eye Closure (PERCLOS). Statistical methods included mixed-effect Poisson models to analyze SCE rates as a function of driving hours. Key findings indicate a decrease in overall cell phone use compared to previous studies, but distinct risks remain based on usage type. Hands-free cell phone use was found to be protective, likely by alleviating driver boredom, whereas hand-held use significantly increased risk by diverting attention from driving tasks. Environmental conditions, such as lighting and traffic density, also influenced the likelihood of engaging in secondary tasks. Regarding fatigue, the study identified the eighth driving hour as having the highest rate of SCE occurrence. Drowsiness prevalence increased significantly with driving duration, particularly in truck drivers, with PERCLOS metrics showing elevated fatigue levels during later hours of shifts. The interaction between secondary tasks and drowsiness further compounded safety risks, with eyes-off-roadway durations being notably longer during SCEs than during baseline driving. The significance of this research lies in its detailed quantification of distraction and fatigue risks in real-world CMV operations. By distinguishing between protective and risky forms of cell phone use, the study suggests that bans on all cell phone use may not be optimal; instead, regulations might benefit from targeting hand-held use specifically. The identification of the eighth driving hour as a peak risk period provides critical data for evaluating hours-of-service regulations. These findings offer FMCSA and industry stakeholders evidence-based insights to refine safety policies, potentially reducing crash rates by addressing specific high-risk behaviors and fatigue patterns in commercial driving.

Key finding

Hands-free cell phone use was found to be protective while hand-held use was risky, and the eighth driving hour showed the highest rate of safety critical event occurrence.

Methodology

naturalistic

Sample size: 245

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
• temporal
• visual
• distraction detection algorithms
• external distraction
• drowsiness detection algorithms

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, observational prevalence, physiological data