Analysis of Naturalistic Driving Data to Assess Distraction and Drowsiness in Drivers of Commercial Motor Vehicles [Research Brief]

NHTSA · 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 Federal Motor Carrier Safety Administration (FMCSA), analyzes naturalistic driving data to assess the impact of distraction and drowsiness on commercial motor vehicle (CMV) drivers. The primary objective was to better understand safety-critical events (SCEs) in the context of driver behaviors and fatigue, aiming to inform safety regulations and operational practices for heavy-vehicle operations. The research utilized data from the original Onboard Monitoring System Field Operational Test (OBMS FOT), comprising over 3.8 million miles of continuous recording from seven fleets across ten locations. Data were collected via cameras and kinematic sensors. Kinematic data were processed using sensor trigger values to identify SCEs, which were manually reviewed and categorized into crashes, near-crashes, crash-relevant conflicts, and unintentional lane deviations. This process yielded 4,102 valid SCEs and 14,198 baseline epochs representing normative driving. Video data were analyzed to identify secondary tasks and fatigue levels. Drowsiness was measured using two methods: Observer Rating of Drowsiness (ORD), a subjective assessment based on video observation, and Percentage of Eye Closure (PERCLOS), an objective metric of eye closure duration. The study calculated odds ratios (ORs) to determine the association between specific secondary tasks and the likelihood of an SCE. The findings revealed that certain tasks increased safety risks while others reduced them. Safety-improving tasks, characterized by ORs less than one, involved mental or physical activity that did not encumber the driver’s hands or divert their eyes from the roadway, such as talking on a hands-free device, singing, or interacting with a passenger. Conversely, safety-degrading tasks, with ORs greater than one, typically involved manual or visual distraction, including reaching for objects, texting, browsing the internet, using electronic dispatching devices, and adjusting mirrors. For instance, reaching for an object had a significant OR of 2.04 for motorcoaches and 3.27 for trucks. Additionally, fatigue levels were highest between 1 a.m. and 6 a.m. The study also noted that ORD identified more instances of drowsiness than PERCLOS, suggesting that human observers may detect moderate fatigue signs before prolonged eye closure occurs. The significance of this research lies in its detailed quantification of how specific secondary tasks affect CMV safety, providing evidence-based insights for regulatory and operational guidelines. However, the study acknowledges limitations, particularly that the data primarily came from local and regional fleets rather than dedicated over-the-road operations, meaning the findings may not fully represent drivers operating for extended hours. Despite this, the large dataset offers valuable groundwork for future research into long-haul driving fatigue and distraction, highlighting the need for further investigation into the distinctions between subjective and objective drowsiness measures.

Key finding

Secondary tasks requiring visual and manual engagement significantly increase the odds of safety-critical events in commercial motor vehicles, whereas tasks involving only cognitive or vocal engagement do not.

Methodology

naturalistic

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
• drowsiness
• distraction detection algorithms
• visual
• temporal

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, behavioral performance data, observational prevalence