Distracted when Using Driving Automation: A Quantile Regression Analysis of Driver Glances Considering Task Type
DOI: 10.3389/ffutr.2022.772910
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 investigates how driving automation, road alignment, and driving experience interact to influence driver distraction, specifically regarding visual glances to secondary tasks. While SAE Level 2 automation (combining Adaptive Cruise Control and Lane Keeping Assist) relieves drivers of manual control, it requires continuous monitoring to handle system limitations. Previous research indicates that such automation increases distraction engagement, but the moderating effects of road demands, particularly road curvature, remain underexplored. The authors aimed to determine if novice and experienced drivers adapt their visual attention differently when using automation on straight versus curved roads. The researchers conducted a secondary analysis using quantile regression on data from two previously reported driving simulator experiments. A total of 32 participants (16 novice and 16 experienced drivers) were included. Half performed non-automated driving, while the other half used ACC and LKA. All participants engaged in a self-paced visual-manual secondary task involving phrase searching on a tablet. The analysis focused on highway drives containing both straight and curved segments. Quantile regression was employed to examine the 15th, 50th, and 85th percentiles of glance durations, allowing for a detailed assessment of the distribution of off-road glances rather than just mean values. Results indicated that driving automation significantly increased glance durations to the distraction task for novice drivers across all percentiles, with the most substantial increases observed in the upper tail (85th percentile). In contrast, experienced drivers did not show increased glance durations at the 50th or 85th percentiles when using automation; in fact, their shortest glances (15th percentile) were shorter with automation than without. Regarding road alignment, experienced drivers adapted to road demands by exhibiting shorter glances on curves compared to straight segments when using automation. Novice drivers, however, failed to demonstrate this adaptive behavior with automation, maintaining longer and more variable glances on curves similar to those on straight roads. Without automation, both groups showed shorter glances on curves, likely due to the increased manual control difficulty. The findings suggest that novice drivers are at higher risk of inappropriate distraction engagement when using Level 2 automation, as they do not regulate their visual attention in response to road complexity as effectively as experienced drivers. The study highlights that automation may exacerbate distraction risks for inexperienced users, particularly on curves where automation limitations may exist. These results imply that novice drivers require additional support or training to safely manage visual distractions while utilizing automated driving systems.
Key finding
Novice drivers exhibit longer, more variable, and less adaptive glance durations toward distracting tasks when using driving automation compared to experienced drivers, particularly failing to reduce glance duration on curved road segments.
Methodology
simulator
Sample size: 32
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.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | — | — | — | 1 | 2026-05-28 |
| archive | success | canonical_url | — | — | 1 | 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 | skipped | — | — | — | 3 | 2026-06-04 |
| promote | success | — | — | — | 1 | 2026-06-04 |
| 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.
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
- Methodological Resource: measurement protocol
- Theoretical Contribution: conceptual framework