Mental workload of common voice-based vehicle interactions across six different vehicle systems
archive: archived pipeline: cataloged verified
Get this paper ↗ (publisher — opens at the source; we link to it, we don't host it)
Summary
This study investigates the mental workload associated with hands-free voice interactions in real-world vehicle infotainment systems. While hands-free technology is marketed as a safety feature to keep drivers' eyes on the road, prior research indicates that auditory-vocal tasks can impose significant cognitive demands, potentially impairing a driver’s ability to detect visual hazards. Previous studies often utilized synthetic or mock-up systems, leaving a gap in understanding how actual Original Equipment Manufacturer (OEM) systems affect cognitive load. This research aimed to quantify the cognitive demands of common voice commands across six different vehicle systems and compare these demands to established baselines for low and high workload tasks. The experimental design involved 36 participants driving six different vehicles: a 2013 Ford Explorer, 2013 Chevy Cruze, 2013 Chrysler 300, 2012 Toyota Prius, 2013 Mercedes E350, and 2013 Hyundai Sonata. Participants performed standardized voice tasks, including making calls and selecting music, while their cognitive workload was measured using three metrics: heart rate via a BioHarness 3, subjective ratings using the NASA TLX scale, and reaction times to peripheral visual stimuli using a Detection Response Task (DRT) device. The study included baseline conditions for single-task driving (low workload) and driving while performing an Operation Span mental math task (high workload). The results revealed significant differences in mental workload across the six vehicle systems. Toyota’s Entune system elicited the lowest cognitive demand, with workload levels comparable to listening to the radio or an audiobook. In contrast, Chevrolet’s MyLink system imposed the highest workload, approaching the levels seen in the high-workload mental math baseline. Systems from Chrysler, Ford, and Mercedes fell in the middle, with demands similar to conversational tasks like talking on a cell phone. Hyundai’s Blue Link system resulted in workload levels slightly higher than the Toyota system but lower than the others. Across all measures—heart rate, subjective ratings, and reaction times—the pattern of differentiation among systems was consistent. 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 suggest that the duration and complexity of the interaction sequence are critical factors in determining cognitive load. Although all voice interactions imposed more demand than single-task driving, none exceeded the high-workload baseline. The authors emphasize that while cognitive distraction is linked to workload, the direct relationship between these workload variations and crash risk remains unclear, necessitating further research to understand the safety implications of specific in-vehicle interface designs.
Key finding
Voice-based interactions across six vehicle systems showed varying but consistently high levels of mental workload, with some systems producing workload comparable to the cognitively demanding OSPAN task.
Methodology
simulator
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 author_sweep_intake on 2026-05-27 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | author_sweep | — | — | 3 | 2026-05-29 |
| archive | failed | pmc | — | — | 19 | 2026-06-04 |
| extract | success | cached | — | — | 5 | 2026-08-10 |
| clean | success | clean | — | — | 2 | 2026-08-10 |
| chunk | success | chunk | — | — | 2 | 2026-08-10 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 2 | 2026-08-10 |
| enrich | skipped | — | — | — | 3 | 2026-07-02 |
| promote | success | — | — | — | 2 | 2026-06-06 |
| summarize | success | llm | qwen3.6-27b-nvidia | summ-v5 | 4 | 2026-08-10 |
| tag | success | vector_similarity | — | — | 28 | 2026-08-11 |
| verify | success | — | — | — | 4 | 2026-08-11 |
Summary generated by qwen3.6-27b-nvidia on 2026-08-10; 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
- Empirical Findings: physiological data
- Theoretical Contribution: theory or model