Driver Distraction: Eye Glance Analysis and Conversation Workload

Hickman, Jeffrey S.; Soccolich, Susan; Fitch, Greg; Hanowski, Richard J. · 2015 · 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) and Virginia Tech Transportation Institute, investigates the relationship between secondary tasks, conversation workload, and visual distraction in commercial motor vehicle (CMV) drivers. The research aims to quantify the risk of safety-critical events (SCEs) associated with cognitive and visual distractions under real-world driving conditions. Specifically, it addresses gaps in understanding how eye glances relate to distraction timing and evaluates whether "spurious baselines" (recordings triggered by non-safety events like railroad crossings) are statistically comparable to random baselines for risk analysis. The researchers utilized naturalistic driving data collected over four months from 6,379 commercial trucks and buses equipped with onboard monitoring systems. These systems recorded video, audio, GPS, and kinematic data, triggering recordings for potential SCEs (e.g., hard braking, speeding) and random baseline periods. The final dataset comprised 1,121 SCEs, 11,562 random baselines, and 10,597 spurious baselines. Data analysts coded secondary tasks into categories such as visual, visual/manual, talking/listening on electronic devices, and talking to passengers. They also analyzed conversation workload via emotion intensity and visual distraction by measuring eyes-off-forward-roadway (EOFR) glances in 0.25-second intervals. Odds ratios were calculated to assess the risk of SCEs associated with these behaviors. The results indicated that talking to passengers significantly increased the likelihood of an SCE compared to both spurious and random baselines. In contrast, talking or listening on electronic devices (handheld or hands-free) did not pose a significant risk. Visual and visual/manual secondary tasks showed no significant impact on SCE risk, though the authors caution that small sample sizes prevent definitive conclusions on safety. Regarding visual distraction, EOFR glances occurring close to the SCE trigger point were significantly associated with higher risk, suggesting that glance timing is critical. Interestingly, longer durations of driver talking were associated with a decreased likelihood of SCEs. Conversation workload analyses were inconclusive due to insufficient data on emotional conversations, which were found to be rare. Additionally, the study confirmed that spurious baselines produced similar results to random baselines, validating their use in future analyses. The findings imply that passenger conversation presents a distinct safety risk for CMV drivers, potentially due to visual distraction or cognitive load, whereas electronic device use does not significantly increase risk in this context. The validation of spurious baselines offers a methodological advantage for future naturalistic driving studies, allowing for more efficient data collection. The study highlights the importance of analyzing glance timing rather than just duration, as glances near event triggers are more predictive of safety deficits. These insights contribute to the broader understanding of distracted driving in commercial fleets, informing potential regulatory or training interventions focused on passenger interactions and visual attention management.

Key finding

Talking to passengers significantly increased the risk of safety-critical events, whereas talking or listening on electronic devices did not.

Methodology

naturalistic

Sample size: 6379

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.

• visual
• temporal
• visual manual
• distraction detection algorithms
• cognitive
• 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: behavioral performance data, observational prevalence
• Methodological Resource: measurement protocol