Countermeasures To Detect and Combat Inattention While Driving Partially Automated Systems

Paras, Carolina Rodriguez; Ferris, Thomas K. · 2023 · ROSA P / Safety through Disruption (Safe-D) University Transportation Center (UTC)

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 addresses the safety risks associated with driver inattention in partially automated vehicles, specifically focusing on the transition of control from automation to the human driver. As vehicle automation levels increase, drivers often experience decreased situational awareness and engage in secondary tasks, leading to delayed or failed takeovers during automation failures. The research investigates whether specific cuing mechanisms—varying by sensory modality (visual, auditory, tactile) and message complexity (simple alerts vs. complex, system-specific guidance)—can effectively combat inattention and facilitate safer, faster manual takeovers. The researchers conducted a driving simulator study with 24 participants using STISIM Drive software. Participants navigated a 30-minute scenario involving suburban and highway driving, including a baseline manual driving period followed by automated driving segments. During the automated phase, participants performed secondary tasks, including a mental rotation game and counting roadside chickens, to simulate distraction. The experiment featured six scripted automation failure events (steering, pedal, or combined failures), some preceded by takeover cues and others without. The cues were presented 2–3 seconds before failure and varied by modality (LED lights, beeping alarms, or vibrotactile feedback) and complexity (general alert vs. specific subsystem identification). Display type and complexity were between-subjects variables. Data collected included driving performance, takeover reaction time, secondary task accuracy, and physiological indices such as heart rate and electrodermal activity. The results indicated no statistically significant differences in driving performance, crash occurrence, secondary task performance, or physiological workload measures based on display type or complexity. However, a clear trend emerged in takeover reaction times: drivers reacted substantially faster to automation failures when preceded by any takeover cue, regardless of modality or complexity, compared to events where no cue was issued. Specifically, events without cues resulted in significantly longer reaction times. Physiological data showed high interindividual variability, with no significant effects attributed to the cue types, though auditory cues were associated with lower electrodermal activity in some participants. The study concludes that issuing takeover cues significantly supports driver situational awareness and reduces reaction times during critical control transitions, even if the specific modality or complexity does not yield statistically distinct advantages in this sample. The authors attribute the lack of significant differences between cue types to the small sample size and the between-subjects design, which introduced noise from interindividual differences. They recommend future research employ within-subjects designs and larger sample sizes to more precisely determine the operational relevance of specific sensory channels and cue complexities. Ultimately, the findings provide evidence that proactive cuing systems are beneficial for mitigating inattention-related risks in partially automated driving environments.

Key finding

Driver reaction times to automation failures are substantially faster when preceded by takeover cues of any sensory modality or complexity compared to events without cues.

Methodology

simulator

Sample size: 24

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.

• automation surprise
• automation
• situational awareness
• takeover transitions
• mode awareness
• automation complacency bias

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