Identifying Outcome Measures to Evaluate Drivers’ Knowledge of Vehicle Automation
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 need to evaluate drivers’ understanding of advanced vehicle technologies, specifically adaptive cruise control (ACC). While these technologies offer safety and convenience benefits, previous research has identified significant gaps in drivers’ knowledge regarding system functionality and appropriate usage. The primary objective was to identify and appraise outcome measures capable of assessing or inferring a driver’s knowledge of vehicle automation, thereby providing a framework for evaluating the effectiveness of training and education programs. The research employed a two-part methodology. Part 1 involved a comprehensive review of scientific literature, engineering standards, and datasets to catalog existing behavioral, performance, and safety measures. This was supplemented by a workshop with subject matter experts to refine the universe of potential measures into a consolidated set. Part 2 consisted of an experimental driving simulator study conducted at two sites with 65 participants. Participants engaged in various driving conditions, including routine driving, system interactions, and takeover scenarios, while their ACC knowledge was assessed prior to the drives. A machine learning approach was utilized to analyze the relationship between specific outcome variables and the participants’ demonstrated knowledge of the system. The findings from Part 1 resulted in a matrix of outcome measures detailing their properties, advantages, and disadvantages. The analysis revealed that individual measures vary significantly in complexity and relevance, suggesting that clusters of measures provide more stable insights than single metrics. In Part 2, the machine learning models indicated that measurement windows focused on system interactions, control takeovers, or routine system operation were most effective in predicting driver knowledge. Eye glance behavior emerged as a prominent predictor across all scenarios, likely due to its direct mapping to driver roles and responsibilities. In contrast, vehicle control and safety measures were less predictive, except during active control situations. Subjective measures, such as confidence and technology acceptance, also proved to be strong predictors of knowledge. The study concludes that researchers and stakeholders should employ a cluster of outcome measures to account for the limitations of individual metrics. Specific recommendations include prioritizing eye glance behavior to corroborate system knowledge, establishing measurement windows around system interactions and takeovers, leveraging subjective measures like confidence, and incorporating demographic and experience data. These findings provide a validated framework for assessing driver knowledge of vehicle automation, which is essential for developing effective training programs and ensuring the safe integration of advanced technologies into traffic systems.
Key finding
Eye glance behavior metrics emerged as the most prominent and useful predictors of drivers' knowledge of adaptive cruise control across various driving scenarios, whereas vehicle control and safety measures were less effective except during active takeover situations.
Methodology
mixed_methods
Sample size: 65
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 bulk_ingest_aaa_foundation on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | aaa_foundation | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 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.
- situational awareness
- acceptance adoption
- automation surprise
- mode awareness
- exposure measurement
- automation
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).
- Methodological Resource: validation psychometrics, measurement protocol
- Theoretical Contribution: computational model