Investigation of Driver Adaptations in a Mixed Traffic Environment
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This study investigates driver adaptations and control transitions (CTs) in mixed traffic environments involving semi-automated vehicles (SAVs), specifically focusing on Adaptive Cruise Control (ACC). The research is motivated by the limitations of ACC systems, which often fail to provide sufficient deceleration during sudden critical events, such as vehicle cut-ins, necessitating a transition from automated to manual control. As automation reduces driver mental workload and situational awareness, sudden increases in task difficulty can lead to delayed or harsh reactions. The primary objectives were to assess behavioral differences between manual and ACC driving, predict CTs using ensemble machine learning (ML) models, and identify key contributing factors using SHAP analysis. The methodology employed a driving simulator study with 30 participants who drove under both manual and ACC conditions. Data collection included vehicle trajectories, driver demographics, and psychological parameters measured via eye-tracking to assess mental workload. Four specific scenarios were developed to capture driver reactions: a base drive, vehicle cut-in, merging from an on-ramp, and lane drops due to construction. The researchers utilized ensemble ML algorithms, including XGBoost and LightGBM, to predict control transitions. Performance was evaluated using accuracy, F1 score, and ROC_AUC metrics. The results indicated significant differences in driving behavior between manual and ACC conditions. Among the tested models, XGBoost achieved the best overall performance, with an accuracy of 0.75, an F1 score of 0.83, and a ROC_AUC of 0.76. SHAP analysis revealed that age, driving experience, relative velocity, and perceived mental workload are the most prominent factors influencing control transitions. The study found that drivers often disengage ACC when the system’s deceleration does not align with their perceived risk or comfort levels, particularly in dense or complex traffic scenarios. The findings underscore the importance of enhancing ACC systems to better accommodate driver safety and comfort in critical traffic situations. By identifying key predictors of control transitions, the research highlights the need for improved human-machine interfaces and automation algorithms that account for individual driver characteristics and dynamic traffic conditions. This work contributes to the broader field of transportation safety by providing a robust predictive framework for understanding driver-automation interactions, ultimately aiming to reduce the frequency of abrupt control transitions and improve overall traffic flow stability.
Key finding
Age, driving experience, relative velocity, and perceived mental workload are the key factors determining control transitions from Adaptive Cruise Control to manual driving.
Methodology
simulator
Sample size: 30
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 bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | success | — | — | — | 2 | 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.
- situational awareness
- following distance
- traffic density
- mental model of traffic
- speed choice
- anticipation
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: computational model, theory or model