Tools for Transport: Driven to Learn With Connected Vehicles
DOI: 10.1111/tops.12565
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper investigates how Advanced Driver Assistance Systems (ADAS) influence driver learning, trust, and performance, specifically focusing on the impact of enhanced vehicle feedback. The authors address the challenge that heterogeneous automation features pose for driver training, noting that while ADAS aims to reduce collisions, misuse often stems from inaccurate mental models of system functionality. The study was motivated by the need to understand if providing drivers with explicit "threat resolution" notifications—indicating when a hazard has ceased to be a danger—improves safety behaviors and subjective experiences compared to warning-only systems. The researchers conducted a between-group experimental study using a high-fidelity virtual reality driving simulator with 36 licensed drivers aged 18–30. Participants were randomly assigned to one of two conditions: "Warning Only," which provided auditory and visual collision warnings, or "Threat Resolution," which added an auditory signal indicating when a threat had resolved. Drivers completed four sessions of simulated urban driving, encountering various critical events, including visually verifiable and non-verifiable threats. The study measured reaction time (RT) to hazards, as well as self-reported trust, effort, and frustration. Driver experience was categorized into novice, intermediate, and experienced groups to assess potential effect modification. Results indicated a significant main effect for condition on reaction time; drivers in the Threat Resolution condition demonstrated faster RTs than those in the Warning Only condition. This performance benefit was consistent across all levels of driving experience, with no significant interaction effects found. Regarding subjective measures, there were no significant differences between conditions in trust, effort, or frustration. However, trust and frustration scores changed significantly across sessions, with frustration decreasing and trust increasing over time for all participants. Exploratory analysis of Session 4 data suggested a potential interaction between experience and trust: experienced drivers in the resolution condition reported higher trust in system performance and process than their counterparts in the warning-only group, whereas novice drivers showed the opposite pattern. The authors conclude that enhanced feedback providing threat resolution improves driver reaction times without negatively impacting trust or increasing frustration. They propose that this benefit arises from helping drivers develop more accurate mental models of the ADAS, particularly by clarifying non-verifiable hazards. The paper argues that learning to use automated tools may follow a phase transition framework rather than a gradual accumulation of experience, implying that mental model acquisition is abrupt and heterogeneous. These findings suggest that ADAS design should prioritize clear resolution feedback to support the rapid development of accurate mental models, which is critical for safe and effective tool use.
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 | 2026-06-07 |
| archive | success | semantic_scholar | — | — | 6 | 2026-06-09 |
| extract | success | cached | — | — | 2 | 2026-06-09 |
| clean | success | clean | — | — | 1 | 2026-06-07 |
| chunk | success | chunk | — | — | 1 | 2026-06-07 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-07 |
| promote | success | — | — | — | 1 | 2026-06-07 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-09 |
| tag | success | vector_similarity | — | — | 8 | 2026-06-11 |
| verify | success | — | — | — | 1 | 2026-06-09 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-09; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- automation surprise
- situational awareness
- automation
- in vehicle coaching
- automaticity skill acquisition
- learner drivers
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: tool software
- Theoretical Contribution: computational model, conceptual framework