Beyond the Dashboard: Investigating Distracted Driver Communication Preferences for ADAS

Hasan, Aamir; McPherson, D. Livingston; Miles, Mellissa; Driggs-Campbell, Katherine; Driggs-Campbell, Katherine · 2024 · arXiv

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 critical issue of distracted driving, which contributes significantly to road fatalities, by investigating how drivers prefer to receive alerts from Advanced Driver Assistance Systems (ADAS). While driver monitoring technologies have improved, current ADAS communication methods often use a static "one mode for all scenarios" approach, which can lead to confusion, over-reliance, or ignored warnings. The authors aim to determine if driver preferences for communication modes (visual, auditory, haptic) vary based on the risk level of the driving scenario and the driver’s distraction state. They also assess driver sentiment toward an Adaptive Communication Module (AdaCoM), a system that would dynamically adjust alert modalities based on real-time driver attention. To answer these questions, the researchers conducted an online user study with 147 participants (144 included in final analysis) recruited via Amazon MTurk and social media. Participants viewed 30 simulated driving videos generated using the CARLA simulator, depicting five scenarios ranging from high-risk (pedestrian collisions) to low-risk (stagnation at a green light). The videos varied by weather conditions and included augmented versions designed to simulate distraction states such as drowsiness or hyper-focus. After viewing each video, participants ranked their top three preferred communication modes from a list of ten options (e.g., sound alerts, vibrations, icons) and indicated their preference for automatic vehicle takeover. The study also included questionnaires measuring perceived safety and comfort regarding in-car audio and video recording for AdaCoM implementation. The results demonstrate that driver preferences are strongly dependent on the hazardous nature of the scenario. For high-risk situations like collisions, participants preferred direct, rapidly interpretable modes such as repeated sound alerts and vibrations. For low-risk scenarios, they favored less urgent reminders like single beeps or spoken language. Visual modes involving non-flashing icons or text were consistently the least preferred across all scenarios. Regarding distraction, statistical analysis using Kendall’s τ and Spearman’s ρ revealed that while preferences do evolve with changing attention states, the correlation between distracted and non-distracted rankings remains positive, suggesting that scenario risk is the primary driver of preference, though personalization remains important. Significantly, the study found strong support for adaptive systems: over 80% of participants reported feeling safer with an AdaCoM system. However, there is a notable privacy barrier; over 60% expressed discomfort with having their audio and video recorded for such systems, likely due to data privacy concerns. The authors conclude that ADAS design should move away from static alerts toward adaptive, scenario-specific communication strategies. They recommend sparsely using dashboard text/icons and prioritizing auditory and haptic alerts for emergencies. Future work should focus on naturalistic studies to validate these findings and address the privacy challenges inherent in implementing adaptive communication modules.

Key finding

Drivers' visual attention allocation extends significantly beyond the immediate driving path, with attention to peripheral environmental cues playing a critical role in situational awareness and hazard detection.

Methodology

lab_experiment

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 discover_arxiv on 2026-05-04 (4 acquisition events logged).

Summary generated by qwen3.6-27b-prismaquant on 2026-06-07; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• external distraction
• distraction detection algorithms
• visual
• feedback modes
• auditory
• 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).

• Applied Guidance: design guidelines
• Empirical Findings: observational prevalence
• Theoretical Contribution: conceptual framework