Using Driver State Detection in Automated Vehicles [supporting dataset]
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 paper addresses the critical safety challenge of control transfers in automated vehicles, specifically focusing on scenarios where drivers may be unfit to retake control due to distraction, drowsiness, or intoxication. As high levels of automation necessitate bi-directional control transfers, the inability of drivers to respond effectively poses a significant safety shortfall. The research investigates the utility of driver state monitoring systems—utilizing eye tracking, head tracking, and other metrics—to mitigate these risks in the context of partial vehicle automation. The study employed data from a production driver monitoring system to evaluate two distinct approaches for utilizing driver state information, comparing them against a baseline condition where automation did not leverage such data. The first approach, termed "attentional maintenance," provided continuous feedback throughout the drive whenever drivers were classified as distracted. The second approach utilized "state-contingent takeover messages," which issued earlier warnings specifically when drivers were detected as distracted during takeover requests. The experimental design aimed to determine how these interventions affected driver performance during unexpected automation failures. The results demonstrated that providing attentional maintenance alerts throughout the drive significantly increased drivers’ situational awareness and enhanced their ability to take over control during unexpected automation failures. This suggests that continuous monitoring and feedback help maintain driver readiness. In contrast, while state-contingent takeover requests improved certain components of the takeover process, the study found limited evidence that this method improved overall takeover performance relative to the baseline. The findings indicate that continuous attentional support is more effective than contingent warnings alone in ensuring driver readiness for control transfers. The significance of this work lies in its validation of driver monitoring systems as a viable tool for enhancing safety in partially automated vehicles. By highlighting the potential utility of real-time driver state data, the study supports the integration of such systems to manage the complex dynamics of human-machine control handovers. The research underscores that maintaining driver awareness through continuous feedback is crucial for addressing the safety shortfalls associated with driver unfitness during automation failures. This dataset, preserved by the SAFER-SIM University Transportation Center, provides empirical evidence supporting the design of automated vehicle systems that prioritize driver state detection to ensure safer transitions of control.
Key finding
Delivering attentional-maintenance alerts throughout an automated drive increased drivers' situational awareness and improved takeover performance during unexpected automation failures, whereas state-contingent takeover warnings showed limited benefit over baseline.
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 (8 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | success | — | — | — | 4 | 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).
- Methodological Resource: tool software, dataset resource
- Theoretical Contribution: conceptual framework