Advanced Driver Assistance System-Equipped Vehicle Datasets Collected in Central Ohio: Final Report
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 report documents the collection and processing of high-resolution, naturalistic datasets featuring Advanced Driver Assistance System (ADAS)-equipped vehicles to address a critical gap in transportation analysis, modeling, and simulation (AMS) tools. Infrastructure owners and operators require accurate data to plan for the integration of connected and automated vehicles (CAVs), yet existing datasets often consist of raw sensor data unsuitable for traffic simulation. The project aimed to provide processed trajectory data that characterizes human-ADAS interactions, enabling researchers to update driver-behavior models and assess the impact of ADAS technologies on transportation system performance. The study was conducted in Central Ohio between January 2020 and June 2023, collecting 144 hours of driving data across highway and arterial environments. The research team utilized two types of SAE Level 2 ADAS-equipped subject vehicles (SVs): "readily identifiable" (RI-ADAS) vehicles with conspicuous sensor stacks and "discreet" (D-ADAS) production vehicles with hidden sensors. This design allowed for the analysis of how adjacent vehicles (AdjVs) react to both the driving behavior and the visual appearance of ADAS-equipped vehicles. Data collection focused on complex scenarios, including vehicle-following, lane-changing, and intersection navigation. The methodology involved a rigorous data-processing pipeline that extracted trajectory data for the SVs and all perceived AdjVs from raw onboard sensor inputs, including LiDAR, cameras, and radar. The pipeline generated output data frames in vehicle, Frenet, map, and Earth-centered, Earth-fixed coordinates, ensuring compatibility with simulation tools. The report details the validation of the processed data, confirming the accuracy of AdjV detection, position, speed, and acceleration. Validation experiments compared sensor-derived metrics against ground truth from instrumented AdjVs, reporting mean errors and standard deviations for headway, speed, and acceleration in both city and highway scenarios. The resulting datasets, made publicly available via the ITS DataHub, include comprehensive metadata and trajectory information for both the subject vehicles and surrounding traffic. The study notes that while the data were collected by project team members rather than the general public, limiting their use for assessing internal driver-ADAS interaction preferences, they are highly effective for evaluating how external drivers alter their behavior—such as gap acceptance and lane-changing willingness—in response to ADAS-equipped vehicles. The significance of this work lies in providing the transportation community with the first large-scale, processed naturalistic datasets of ADAS vehicle operations. These resources enable the development of calibrated microsimulation models that account for CAV behaviors, supporting data-informed infrastructure investment decisions. By facilitating the characterization of human-ADAS interactions, the datasets help ensure that future transportation systems are designed to accommodate emerging vehicle technologies, ultimately maximizing system performance and safety as CAV adoption increases.
Key finding
The project successfully developed a methodology to collect and process raw sensor data from ADAS-equipped vehicles into high-resolution, naturalistic trajectory datasets that characterize human-ADAS interactions in complex driving environments.
Methodology
naturalistic
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).
- Methodological Resource: dataset resource, tool software, validation psychometrics