Mental workload of voice interactions with 6 real-world driver interfaces
DOI: 10.17077/drivingassessment.1543
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 cognitive demands of hands-free voice interactions with six real-world Original Equipment Manufacturer (OEM) infotainment systems, addressing a gap in prior research that relied heavily on synthetic or mock-up systems. While hands-free technology is intended to enhance safety by keeping drivers’ eyes on the road, previous literature suggests that speech-to-text interactions may impose significant mental workload, potentially impairing visual detection and response capabilities. The authors aimed to determine how cognitively demanding actual OEM systems are, how workload varies between different manufacturers, and how these demands compare to established baselines such as single-task driving, conversational phone use, and high-load mental arithmetic. The experimental design involved 36 participants driving six different vehicles (Ford, Chevrolet, Chrysler, Toyota, Mercedes, and Hyundai) while performing standardized voice tasks, including placing calls and selecting music. Mental workload was assessed using a multi-modal approach: physiological data via heart rate monitoring, behavioral data via a Detection Response Task (DRT) measuring reaction times to peripheral visual stimuli, and subjective ratings using the NASA TLX scale. These measures were combined into a composite workload score. Baseline conditions included single-task driving (low workload) and driving while performing an Operation Span mental math task (high workload). Results indicated significant variability in cognitive demand across the six systems. Toyota’s Entune system elicited the lowest workload, comparable to listening to the radio or an audiobook, and significantly lower than the other systems. In contrast, Chevrolet’s MyLink system imposed the highest workload, approaching the level of the high-demand mental math baseline. Hyundai’s Blue Link produced workload levels similar to conversational phone use, while Chrysler, Ford, and Mercedes systems fell in the middle, comparable to error-free speech-to-text tasks. Reaction times were significantly slower during voice interactions than during single-task driving, with Ford’s MyFord Touch showing notably delayed responses. The primary driver of this variance appeared to be the duration of the interaction required to complete tasks. The study concludes that while well-executed voice systems impose minimal additional cognitive demand, poorly executed systems can significantly elevate mental workload, potentially creating safety risks. The findings demonstrate that real-world OEM systems vary widely in their cognitive impact, ranging from negligible distraction to levels approaching complex mental arithmetic. However, the authors note that the association between cognitive distraction and actual crash risk remains unclear, and further research is needed to understand how these workload variations translate to real-world safety outcomes.
Key finding
Mental workload during voice interactions varied significantly by system, with Toyota's Entune imposing minimal demand and Chevrolet's MyLink imposing high demand comparable to complex cognitive tasks.
Methodology
on_road
Sample size: 36
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 google_drive_download on 2026-05-06 (2 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | — | — | — | 1 | 2026-05-06 |
| archive | success | canonical_url | — | — | 12 | 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 | success | openalex | — | — | 2 | 2026-05-08 |
| promote | success | — | — | — | 1 | 2026-05-06 |
| 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).
- Applied Guidance: design guidelines
- Theoretical Contribution: theory or model