Empirical Validation of Human-Centered Driving Style Parameterization in Highly Automated Vehicles
DOI: 10.54941/ahfe1007172
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 relationship between users’ natural manual driving behavior and their preferred driving styles for highly automated vehicles (HAVs). While prior research established that users can meaningfully interact with parameterized driving styles via human-machine interfaces (HMIs) and converge on stable preferences, it remained unclear whether these preferences mirrored users’ actual manual driving dynamics. The authors sought to validate whether automated driving personalization should aim to imitate individual manual driving styles or if users prefer distinct automated behaviors. The researchers conducted a within-subjects driving simulator experiment with fourteen participants. The study utilized a high-fidelity simulator featuring a VW Golf 7 cabin on a 6-DOF motion system and SILAB simulation software. Participants completed two conditions: a manual driving session where they drove naturally, and an automated driving session where they adjusted HMI parameters controlling speed, acceleration, lane positioning, and following distance. Objective vehicle performance data were recorded for both conditions. The authors extracted four key features—mean speed, mean absolute jerk (smoothness), mean lateral position deviation, and mean time headway—and analyzed them using K-means clustering, principal component analysis, and participant-wise similarity metrics (Euclidean distance and cosine similarity). The results revealed distinct driving style clusters (conservative, standard, aggressive) for both manual and automated conditions. However, participant-wise similarity analysis showed a significant divergence between manual behavior and preferred automated styles. Cosine similarity values were predominantly negative, indicating that automated preferences were often inversely related to natural manual driving. Across all participants, automated driving was consistently characterized by lower speeds, smoother acceleration (lower jerk), more centered lane positioning, and larger following distances compared to their manual driving. These trends persisted regardless of the participant’s manual driving cluster. The findings suggest that users do not expect automated vehicles to imitate their personal driving styles. Instead, when relinquishing control, users prioritize comfort, predictability, and perceived safety, favoring more conservative and stable automated behavior. This implies that adaptive systems relying solely on behavioral imitation may fail to meet user expectations. The study concludes that effective personalization in HAVs should combine predefined semantic presets with flexible adjustment mechanisms, allowing users to express preferences for safety and comfort that differ from their manual driving habits. This insight is critical for designing user-centered automated driving systems that enhance trust and acceptance.
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 | 2026-08-09 |
| archive | success | canonical_url | — | — | 1 | 2026-08-09 |
| extract | success | pdftotext | — | — | 4 | 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 |
| promote | success | — | — | — | 1 | 2026-08-09 |
| summarize | success | llm | qwen3.6-27b-nvidia | summ-v5 | 2 | 2026-08-10 |
| tag | success | vector_similarity | — | — | 17 | 2026-08-11 |
| verify | partial | — | — | — | 2 | 2026-08-10 |
Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified_with_issues.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- automation
- automation surprise
- acceptance adoption
- trust calibration
- passenger motion sickness comfort
- steering pattern
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
- Theoretical Contribution: computational model, conceptual framework