Driving with Partial Driving Automation Systems: Developing Effective Training that Drivers Will Use

AAA Foundation for Traffic Safety · 2025 · AAA Foundation for Traffic Safety

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 gap between the availability of formal training for partial driving automation systems and drivers’ actual engagement with such instruction. While previous research indicates that formal instruction improves driver understanding of these technologies, most drivers currently learn through trial and error rather than seeking structured education. The research aimed to identify training features that would increase the likelihood of drivers voluntarily choosing to engage with and complete formal training, utilizing principles of adult learning to guide the development. The project employed a multi-phased methodology involving expert consultation, focus groups, and an on-road experiment. Initially, a workshop with multidisciplinary experts evaluated four training concepts: a booklet, an in-vehicle video, a live in-person demonstration, and interactive in-vehicle training. These insights informed draft modules tested in focus groups with drivers who owned vehicles equipped with partial automation. Participants reported learning primarily through trial and error and rejected in-person demonstrations, preferring self-paced, transparent, and easy-to-use training accessible within the vehicle. The final phase was an on-road study where participants drove a 2023 Ford Mustang Mach E on a 107-mile route. Participants were not instructed to use available training materials but were given access to a flip-book, an in-vehicle video (for half the group), or short interactive training messages triggered at preset locations (for the other half). Engagement was measured via in-vehicle cameras and post-drive surveys. The findings indicate that interactive in-vehicle training is the most promising approach for increasing driver engagement. Participants were significantly more likely to use the interactive training compared to the video or flip-book. More than 80% of those with access to the interactive modules completed most or all of the training, with evidence suggesting they paid attention to the content. Additionally, 66% to 74% of participants reported they would use any of the examined training types if available in a rental car. However, the study noted significant limitations regarding real-world applicability. The interactive training required strict safeguards, such as fixed routes with light traffic and triggers only during safe driving conditions, which may be difficult to implement broadly. Furthermore, the study measured engagement rather than training efficacy, and further research is needed to determine if drivers would engage with such training in uncontrolled, real-world contexts.

Key finding

Drivers were significantly more likely to voluntarily engage with and complete interactive in-vehicle training compared to video or booklet formats for learning about partial driving automation systems.

Methodology

mixed_methods

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).

StageOutcomeToolModelPromptAttemptsCompleted
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).