The distraction potential of driving a partially automated vehicle through a construction zone

Biondi, F; Sahoo, P; Jajo, N · 2025 · Scientific Reports

DOI: 10.1038/s41598-025-93588-z

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 the distraction potential and cognitive workload of drivers using partially automated (SAE Level 2) vehicles in construction zones, a high-risk driving environment. While manufacturers often market these systems as safety enhancements, regulatory investigations have linked partial automation to driver complacency and misuse. The authors aimed to determine if drivers maintain adequate alertness and visual attention when transitioning from normal road conditions into construction zones, where crash risks are significantly elevated. Specifically, the research examined whether the presence of a construction zone prompts drivers to increase their monitoring of the forward roadway or if the distraction patterns associated with automation persist in these demanding scenarios. The experiment employed a within-subjects factorial design with 21 participants driving a vehicle equipped with Adaptive Cruise Control and Lane Keeping Assist. Participants drove through three distinct zones—pre-construction, construction, and post-construction—in both manual and Level 2 automated modes. Cognitive workload was measured using a vibrotactile Detection Response Task (DRT), recording reaction times and hit rates. Visual attention was tracked via cameras coding glances toward four areas of interest: the forward roadway, vehicle touchscreen, side mirrors, and rearview mirror. Data analysis utilized Bayes factors to evaluate evidence for or against differences in workload and glance allocation across driving modes and zones. Results indicated no significant difference in cognitive workload, as measured by DRT reaction times, between manual and automated driving modes or across the different zones. However, DRT hit rates decreased from pre-construction to construction zones, suggesting a potential increase in workload, though this finding was interpreted with caution due to divergent reaction time data. Crucially, glance allocation analysis revealed that drivers spent significantly less time looking at the forward roadway (91%) and more time looking at the vehicle’s touchscreen (6.14%) during Level 2 driving compared to manual driving. Notably, this pattern did not change when entering the construction zone; drivers failed to increase their visual attention to the road despite the heightened hazard potential, maintaining the same level of distraction toward the touchscreen as in pre-construction areas. The findings challenge the notion that partially automated systems improve safety in complex environments. The persistence of distraction behaviors in construction zones suggests that drivers do not self-regulate their attention appropriately when road conditions become more demanding. This indicates a "pernicious" effect of partial automation, where the system’s convenience features may lead to sustained inattentiveness even in accident-prone areas. The authors conclude that these systems may not mitigate risk in construction zones and argue for engineering solutions that automatically disengage automation in such high-risk scenarios, rather than relying on driver discretion.

Key finding

Drivers using partially automated systems spent significantly more time looking at the vehicle's touchscreen and less time monitoring the forward roadway compared to manual driving, and this distraction pattern persisted without improvement when entering construction zones.

Methodology

on_road

Sample size: 21

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 openalex_abstract on 2026-05-08 (7 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.

• work zones
• temporal
• visual
• situational awareness
• manual
• attention allocation

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
• Theoretical Contribution: conceptual framework, theory or model