Your Interface, Your Control: Adapting Takeover Requests for Seamless Handover in Semi-Autonomous Vehicles
DOI: 10.48550/arxiv.2506.01836
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 addresses the need for adaptive Takeover Request (ToR) systems in semi-autonomous vehicles, aiming to improve safety and driver experience by personalizing warning strategies based on driver state and context. Motivated by the limitations of static warning systems, the authors propose an adaptive approach that adjusts ToR timing and visual display location. The researchers conducted two user studies using a driving simulator. Study 1 (Display Type) involved 37 participants comparing Head-up Displays (HUD) versus Head-down Displays (HDD) during hazardous takeover events in rural and urban environments. Study 2 (Time Budget) involved 29 participants evaluating varying time budgets (4, 8, and 12 seconds) for non-hazardous system failures. Participants performed Non-Driving Related Tasks (NDRTs) such as visual search, text entry, or peripheral detection. Data collection included reaction times, driving performance metrics, gaze tracking, EEG for mental workload, and subjective NASA-TLX assessments. The findings reveal that optimal ToR strategies depend on environmental complexity and event severity. For non-hazardous events in high-complexity environments, longer time budgets and HUDs are recommended. Conversely, for hazardous events in low-complexity environments, shorter time budgets and HDDs yield better performance. The studies demonstrated that adapting these parameters based on context significantly enhances situational awareness and takeover quality. These results provide actionable guidelines for designing adaptive ToR systems, suggesting that implicit personalization can improve handover safety. By tailoring warnings to specific driving contexts and driver states, the proposed strategies offer a more effective alternative to static, one-size-fits-all approaches in conditional automation.
Key finding
Customizable vehicle interfaces can reduce cognitive load and improve task performance when drivers have the opportunity to adapt the interface to their preferences, but poorly designed customization options can increase workload and distraction.
Methodology
lab_experiment
Sample size: 40
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 discover_arxiv on 2026-05-04 (4 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | author_sweep | — | — | 4 | 2026-05-27 |
| archive | success | — | — | — | 1 | 2026-05-04 |
| extract | success | cached | — | — | 2 | 2026-06-07 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-04 |
| promote | success | — | — | — | 1 | 2026-05-04 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-07 |
| tag | success | vector_similarity | — | — | 16 | 2026-06-11 |
| verify | success | — | — | — | 1 | 2026-05-08 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-07; 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).
- Empirical Findings: behavioral performance data
- Methodological Resource: measurement protocol
- Theoretical Contribution: conceptual framework