Characterizing Level 2 Automation in a Naturalistic Driving Fleet
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 addresses the critical need to understand driver adaptations and usage patterns of SAE Level 2 (L2) automation features in naturalistic driving conditions. As L2 systems, which combine adaptive cruise control (ACC) and lane keeping assistance (LKAS), become more prevalent in non-luxury consumer vehicles, understanding how drivers interact with these systems is essential for safety and system design. The research specifically investigates the environmental conditions, roadway types, and trip characteristics associated with L2 activation and deactivation, as well as the frequency and nature of takeover requests. The researchers leveraged data from the Virginia Tech Transportation Institute (VTTI) L2 Naturalistic Driving Study, analyzing 47 vehicles equipped with L2 automation. The study focused on isolating epochs where ACC and LKAS were used in tandem. The methodology involved characterizing activation timing, location, and duration, as well as analyzing driver-initiated overrides and system-initiated deactivations. The analysis examined metrics such as time-of-day, weather, traffic conditions, and roadway types to determine compatibility with the systems' operational design domains. Additionally, the study categorized takeover requests to understand the situations prompting drivers to resume control. The results indicated that L2 feature usage did not significantly differ from general driving periods regarding time-of-day or calendar metrics. Most activations occurred on motorways, aligning with design expectations. L2 features were active for an average of 7.2 minutes per trip, which lasted an average of 22.8 minutes, representing approximately 32% of the trip duration. Driver-initiated overrides were primarily executed through braking or acceleration, while steering-based overrides were minimal and likely associated with lane changes without turn signals. Regarding system-initiated deactivations, intervention requests were the most common takeover request, followed by alerts due to insufficient driver hand contact with the steering wheel. The study also noted evidence of potential system misuse, though further operationalization is needed to assess its prevalence. The findings suggest that as L2 features penetrate the broader U.S. vehicle fleet, their usage patterns will likely mirror those observed in luxury vehicles, with common usage on highways and during clear weather. The predominance of longitudinal overrides (braking/accelerating) over lateral ones indicates specific driver interaction habits. The high frequency of intervention requests highlights the importance of system reliability and driver monitoring. These insights are significant for improving L2 system design, enhancing safety protocols, and developing strategies to mitigate misuse and complacency. The study underscores the need for continued research into driver behavior and system performance to ensure safe integration of automation into the national fleet.
Key finding
Level 2 automation features were activated for approximately 32% of trip duration, predominantly on motorways, with driver overrides mainly occurring via braking or acceleration and takeover requests most frequently triggered by system interventions or lack of hand contact.
Methodology
naturalistic
Sample size: 47
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.
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: observational prevalence
- Methodological Resource: dataset resource
- Theoretical Contribution: conceptual framework