Typology of Behavioral and Emotional Reactions to Uncomfortable Automated Driving Operations
DOI: 10.54941/ahfe1005204
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 variability in driver reactions to uncomfortable automated driving maneuvers, addressing the critical role of driving comfort in the public acceptance of automated vehicles. The research aims to develop a typology of behavioral and emotional responses to inform comfort-adaptive automation systems that can intervene early to prevent discomfort or unsafe take-overs. Specifically, the study evaluates whether facial expression analysis, particularly the detection of "surprise," can serve as a reliable indicator of discomfort when combined with behavioral monitoring. The researchers conducted a driving simulator study with 74 participants (aged 19–75, balanced by gender) who performed non-driving-related tasks (answering emails) during highly automated driving. The experimental design included a critical scenario where the automated vehicle approached a stationary truck with late, strong braking, creating a potentially uncomfortable situation. Data collection involved video recording of facial expressions using Visage FaceTrack software and manual annotation of glances and task interruptions. A clustering analysis was applied to categorize participants based on three behavioral indicators: whether they resumed manual control, whether they interrupted their laptop work, and their visual attention toward the driving situation. Emotional reactions were quantified by comparing peak "surprise" values during the approach to a baseline period. The analysis identified five distinct reaction clusters. Cluster 1 ("not noticed," 9%) showed no behavioral or emotional reaction, indicating high reliance on automation. Cluster 2 ("quick check," 15%) briefly glanced ahead with minimal surprise (4.8% increase). Cluster 3 ("observation," 30%) stopped working and observed the situation without taking control, exhibiting the highest surprise increase (9.7%). Cluster 4 ("quick take-over," 31%) grasped the steering wheel and braked late, showing significant surprise (9.2%) and the lowest post-experiment trust and acceptance. Cluster 5 ("planned take-over," 15%) took control early and intensively monitored the situation, showing the lowest surprise increase (3.8%). Significant differences were found across clusters in demographics, initial attitudes, and changes in trust and acceptance. The findings demonstrate that reactions to identical automated maneuvers vary considerably, necessitating tailored rather than uniform comfort strategies. The study concludes that "surprise" is a promising emotional indicator for discomfort, but its detection must be context-aware, triggered by the interruption of non-driving tasks and directed visual attention to avoid false alarms. The authors suggest a threshold of a 5% increase in surprise relative to an individual baseline for initiating adaptive interventions. These results support the development of co-active vehicle-driver systems that monitor real-time emotional and behavioral states to enhance safety and comfort, though further validation in real-world conditions is required.
Key finding
Drivers exhibit five distinct typologies of behavioral and emotional reactions to uncomfortable automated driving maneuvers, necessitating personalized comfort-adaptive interventions.
Methodology
simulator
Sample size: 74
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.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-06-05 |
| archive | success | canonical_url | — | — | 1 | 2026-06-06 |
| extract | success | cached | — | — | 3 | 2026-06-15 |
| clean | success | clean | — | — | 1 | 2026-06-07 |
| chunk | success | chunk | — | — | 1 | 2026-06-07 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-07 |
| promote | success | — | — | — | 1 | 2026-06-05 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-15 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | partial | — | — | — | 1 | 2026-06-07 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-15; verification: verified_with_issues.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- automation surprise
- automation
- acceptance adoption
- takeover transitions
- trust calibration
- situational awareness
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, self report data
- Theoretical Contribution: conceptual framework