AUTOMATED DRIVING SYSTEMS: COMPARISON OF TRAINING METHODS’ EFFECTIVENESS
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 addresses the critical need for effective driver training as automated driving systems (ADS) become more prevalent, particularly given the limitations of current driver knowledge regarding system boundaries and safety protocols. Motivated by the co-existence of varying automation levels and the human factor's role in safety, the research compares the effectiveness of three training methods: practical simulator training, e-learning, and reading a short user manual. The goal was to determine which method best facilitates driver-vehicle interaction, ensures reactive capability in dangerous situations, and conveys an understanding of system limitations. The experimental design involved 81 licensed drivers (aged 18–65) with limited prior experience in automated vehicles. Participants were divided into three groups corresponding to the training methods. Testing was conducted on a high-fidelity driving simulator equipped with a Level 4 automation system. The procedure included pre-training assessments, an adaptation drive, the assigned training, and a standardized test drive scenario. This scenario featured normal driving, crash events requiring a Request to Intervene (RtI), and reduced visibility conditions (fog) where drivers had to manually retake control without a system prompt. Objective metrics included activation time, number of activation attempts, reaction time to RtI, and accuracy in bad weather. Subjective metrics included self-assessment versus trainer assessment and overall training satisfaction. The results demonstrated that practical training yielded the most effective performance outcomes. Participants in the practical group showed significantly faster total activation times and fewer attempts to engage the automation system compared to those who read the manual or used e-learning. Specifically, practical training led to faster reactions in initial activation scenarios and during weather-related interventions. In terms of reaction time to RtI, the practical group also outperformed the manual group. Regarding safety-critical behavior in fog, training type was a significant predictor of correct manual takeover; notably, only two participants from the manual group correctly retaken control, whereas practical and e-learning groups performed similarly and better. Subjectively, practical training received the highest satisfaction scores and recommendation rates. However, the study highlighted a significant discrepancy in self-assessment, with 23–43% of drivers overestimating their skills compared to trainer evaluations, a risk factor for accidents. The significance of this research lies in its evidence that hands-on, practical training is superior for developing the specific skills required to safely operate automated vehicles, particularly in handling system boundaries and emergencies. While e-learning and manuals are less effective for immediate performance, they were still rated highly for meeting expectations. The findings imply that regulatory bodies and manufacturers should prioritize practical, simulator-based training curricula to mitigate risks associated with driver overconfidence and inadequate understanding of ADS limitations. This supports the broader goal of enhancing road safety as automation technologies are integrated into public transport.
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 | 2026-06-18 |
| archive | success | canonical_url | — | — | 1 | 2026-06-25 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-18 |
| chunk | success | chunk | — | — | 1 | 2026-06-18 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-18 |
| promote | success | — | — | — | 1 | 2026-06-18 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-18 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- driverless ads
- simulator training transfer
- automation surprise
- automation
- learner drivers
- 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).
- Applied Guidance: countermeasure evaluation
- Methodological Resource: tool software
- Theoretical Contribution: computational model