Computational Models for In-Vehicle User Interface Design: A Systematic Literature Review
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This systematic literature review addresses the gap between the theoretical development of computational models for in-vehicle user interface (UI) design and their practical adoption in the automotive industry. Driver distraction, particularly resulting from Non-Driving Related Tasks (NDRTs) on modern infotainment systems, is a leading cause of vehicle crashes. While regulatory bodies like Euro NCAP are mandating safer interfaces, current evaluation methods rely heavily on resource-intensive empirical user studies. Computational models offer a promising alternative by automating distraction evaluation earlier in the design process, yet they have not become standard industrial tools. The authors aim to analyze the state of the art to understand why these models remain disconnected from designer needs and to identify research gaps. The study employs a systematic review methodology following the PRISMA 2020 checklist. The authors searched three databases (Scopus, IEEE Xplore, and ACM Digital Library) using specific keywords related to driver behavior, distraction, and computational modeling. The initial search yielded 1,679 records, which were filtered through title/abstract screening and full-text assessment based on strict inclusion criteria, such as the requirement for a computational model that quantifies the effect of secondary tasks on driver behavior. The process included forward and backward snowballing to ensure comprehensive coverage. Ultimately, 34 papers were selected for detailed data extraction and analysis. The authors categorized these models across eight dimensions, including target variables, model inputs, and intended applications, using a mixed a priori and inductive coding approach. The analysis reveals that existing models primarily focus on isolated phenomena rather than holistic UI evaluation. The most common target variables are vision-related metrics, such as glance duration and frequency (47% of papers), followed by driving performance metrics like lateral and longitudinal control (32%). Fewer models address task performance (26%) or mental workload/distraction (23%). The review identifies several categories of computational models, including cognitive architectures like ACT-R, task decomposition models like GOMS, Queueing Networks, and Machine Learning approaches. A key finding is that most models predict latent states (e.g., distraction) based on physiological or behavioral data, or predict behavior based on environmental inputs, rather than directly linking specific UI design features to distraction outcomes. Consequently, the predictions are often not detailed enough to inform specific design decisions. The significance of this work lies in its identification of critical research gaps that hinder the industrial adoption of computational models. The authors conclude that current approaches are too disconnected from the practical needs of automotive UI designers, who require tools that can evaluate complex, holistic systems early in the design cycle. By mapping the existing landscape and highlighting the lack of models that directly connect design artifacts to distraction metrics, the review provides a roadmap for future research. It suggests that developing models capable of making detailed, design-specific predictions is essential for integrating computational evaluation into standard automotive UX workflows, thereby improving road safety and design efficiency.
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 | 2026-06-05 |
| archive | success | canonical_url | — | — | 13 | 2026-06-09 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| 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 | 2026-06-05 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | success | — | — | — | 1 | 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).
- Applied Guidance: design guidelines
- Theoretical Contribution: conceptual framework, computational model