Detection of distracted driving through the analysis of real-time driver, vehicle, and roadway volatilities
DOI: 10.1080/19439962.2024.2341393
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This study addresses the critical safety issue of distracted driving, which contributes significantly to traffic crashes and fatalities. While existing standards often focus on visual distraction, this research aims to detect both visual and cognitive distractions by analyzing real-time volatilities in driver biometrics, vehicle kinematics, and roadway surroundings. The primary motivation is to enable early detection systems that can provide proactive feedback to drivers and surrounding vehicles, thereby reducing crash risk. The researchers conducted experiments using a Multimodal Virtual Reality Simulator at the University of Tennessee. Twenty-six licensed drivers participated in driving scenarios involving a visual Detection Response Task (DRT) with increasing complexity (4x4 to 8x8 grids of arrows), corresponding to undistracted, mild, moderate, significant, and severe distraction levels. Data were collected via sensors, including an HTC Vive Pro headset for eye-tracking, capturing metrics such as eye openness, gaze, vehicle speed, acceleration, steering, and distances to lane centerlines and other vehicles. These raw data were aggregated into 3-second intervals to calculate volatility measures, specifically the Coefficient of Variation (CV) and Mean Absolute Deviation (MAD). The study employed three modeling approaches to classify distraction levels: a Panel Ordered Logit Model, a Random Forest classifier, and an Artificial Neural Network. The results indicated that driving volatility increases with distraction severity. The Panel Ordered Logit Model identified driver gaze, CV of eye movements, CV of vehicle speed, CV of distance from the lane centerline, and CV of distance to the following vehicle as statistically significant predictors of distraction. Specifically, higher variability in eye movements and speed strongly correlated with significant and severe distraction states. The model achieved a classification accuracy of 67.58% on the test dataset. The findings suggest that instantaneous variations in these specific biometric and kinematic parameters serve as reliable indicators of degraded driving performance. The significance of this work lies in its contribution to the development of Advanced Driver Assistance Systems (ADAS) capable of detecting non-visual and cognitive distractions. By leveraging real-time volatility metrics, the proposed method supports the safe systems approach through proactive safety measures. The integration of these detection algorithms into vehicle automation technologies offers potential for timely warnings to drivers and nearby vehicles, fostering safer user behavior and reducing the likelihood of safety-critical events.
Key finding
Driver gaze and the coefficients of variation in vehicle speed, driver eye movements, vehicular distances from the lane centreline, and the following vehicle significantly impact the detection and classification of distracted driving.
Methodology
simulator
Sample size: 26
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 scout_discovery on 2026-05-08.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | partial | scout | — | — | 2 | 2026-05-08 |
| archive | success | canonical_url | — | — | 6 | 2026-06-06 |
| extract | success | cached | — | — | 3 | 2026-06-10 |
| clean | success | clean | — | — | 1 | 2026-06-04 |
| chunk | success | chunk | — | — | 1 | 2026-06-04 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-04 |
| enrich | success | — | — | — | 1 | 2026-05-08 |
| promote | success | — | — | — | 1 | 2026-05-08 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
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.
- distraction detection algorithms
- visual
- external distraction
- mind wandering
- peripheral attention
- 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: behavioral performance data, physiological data
- Theoretical Contribution: conceptual framework