Mapping Comprehension of ADAS across Different Road Users
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 investigates road users’ comprehension of Advanced Driver Assistance Systems (ADAS), specifically Adaptive Cruise Control (ACC) and Lane Keeping Assistance (LKA). While ADAS aims to enhance safety, existing research indicates significant gaps in drivers’ understanding of these technologies. This project, a collaboration between the AAA Foundation for Traffic Safety and the SAFER-SIM University Transportation Center, sought to characterize drivers with weak versus strong ADAS understanding across demographics, experiences, and perceptions. Additionally, it aimed to identify distinct driver clusters based on the quality of their mental models and their confidence levels, particularly to identify groups prone to mishandling automation due to high confidence despite low knowledge. The researchers conducted an online survey between February and April 2023, utilizing a sample of 2,529 U.S. adults aged 18 to 93. The sample was representative of the U.S. population, with participants recruited from all 50 states, Puerto Rico, and Washington, DC. The majority of respondents were male (51%), white (76%), held college degrees (69%), and drove at least weekly (96%). The survey, administered via Qualtrics, covered demographics, driving experience, ADAS experience including a Mental Model Assessment, learning preferences, and technology perceptions. Participants received $5 compensation. Key findings revealed that drivers with strong ADAS understanding were, on average, six years younger than those with weak understanding. Interestingly, both groups rated their own knowledge similarly, yet the strong-understanding group reported lower familiarity and trust in ACC and LKA. Learning methods differed significantly: the strong-understanding group relied on trial and error, while the weak-understanding group used owner’s manuals. Cluster analysis identified four groups: Weak Confident (WC), Weak Unconfident (WU), Strong Confident (SC), and Strong Unconfident (SU). Males were overrepresented in confident clusters. The WC cluster, despite having weak mental models, reported the highest driving confidence, safety ratings, and frequent ADAS use. Ownership of ADAS increased confidence but did not improve actual knowledge quality. Confident clusters (WC and SC) were more likely to own ADAS-equipped vehicles and learn via diverse sources, including the internet and dealerships. The study concludes that ADAS education should prioritize teaching system limitations and operational design domains to bridge knowledge gaps. Since confidence does not correlate with accurate mental models, and ownership may inflate confidence without improving understanding, targeted educational strategies are necessary. Age and sex are significant factors influencing learning preferences and mental models, suggesting that future training programs should be tailored to these demographic variables to mitigate risks associated with inappropriate automation use.
Key finding
Drivers with weak understanding of ADAS often exhibit high confidence in their knowledge, while frequent system use and ownership do not necessarily lead to stronger mental models of the technology.
Methodology
survey
Sample size: 2529
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.
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: observational prevalence, self report data