Toward Computational Simulations of Behavior During Automated Driving Takeovers: A Review of the Empirical and Modeling Literatures
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This review article addresses the critical safety challenges associated with automated-to-manual control transitions in automated vehicles, specifically focusing on the "take-over" process where human drivers must resume control from automation. The motivation stems from the fact that while automated driving technologies promise significant safety improvements, current systems at SAE levels 2–4 still present risks during these transitions, particularly when drivers are disengaged or "out-of-the-loop." The authors aim to identify factors influencing take-over performance and determine which computational driver models can accurately simulate these behaviors to aid in safer system design. The study employs a systematic literature review methodology, searching five major databases (TRID, Compendex, Scopus, Web of Science, and Google Scholar) for peer-reviewed articles published from 2012 onward. The review is divided into two parts: empirical studies of automated vehicle take-overs and quantitative driver modeling. Inclusion criteria required empirical data on control transitions for SAE levels 2–4 and models predicting driver behavior relevant to take-over phases. After screening, 83 articles on take-overs and 60 articles on driver modeling were selected for detailed analysis. The authors examined factors such as time budget, secondary tasks, take-over request modality, driving environment, and driver-specific conditions like fatigue or alcohol impairment. The review finds that several factors significantly influence both take-over time and post-take-over control quality. Specifically, the available time budget, repeated exposure to take-overs, silent system failures, and handheld secondary tasks significantly impact the time required for drivers to respond. Additionally, the modality of the take-over request, driving environment, non-handheld secondary tasks, level of automation, trust, fatigue, and alcohol impairment significantly affect the quality of control after the take-over. Notably, drivers respond similarly to manual emergencies and automated take-overs, albeit with a delay. The authors conclude that existing braking and steering models developed for manual driving may be applicable to automated take-overs. Evidence accumulation models are identified as particularly promising for capturing these complex effects. The significance of this work lies in providing a structured foundation for developing computational simulations of driver behavior during automated driving take-overs. By identifying key influential factors and suitable modeling approaches, the review enables designers to approximate the safety impacts of design choices more accurately. This facilitates faster, large-scale testing of potential take-over scenarios, helping to identify high-risk situations and guide system modifications. The findings support the integration of accurate driver models into safety assessments, which is crucial given the difficulty of obtaining conclusive safety proof through real-world testing alone for emerging automated vehicle technologies.
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 | OpenAlex-citations | — | — | 1 | 2026-06-17 |
| archive | success | semantic_scholar | — | — | 6 | 2026-06-25 |
| extract | success | cached | — | — | 2 | 2026-06-25 |
| 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 | 2026-06-17 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-25 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-18 |
| verify | partial | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-25; verification: verified_with_issues.
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: behavioral performance data
- Theoretical Contribution: conceptual framework, computational model