Connected and Automated Vehicle (CAV) Data Infrastructure and Access Phase 1 and 2
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 details the development and implementation of a formal data access infrastructure for Connected and Automated Vehicle (CAV) naturalistic driving data (NDD) held by the University of Michigan Transportation Research Institute (UMTRI). The project was motivated by the high demand from researchers for secondary use of NDD collected over three decades, which previously lacked a standardized, secure, or equitable access process. The primary challenge involved balancing open research access with the protection of personal identifiable information (PII) and proprietary data elements, as well as managing the administrative burden on UMTRI staff. The project was conducted in two phases. Phase 1 focused on establishing governance and procedures, including the creation of a data management committee comprising Principal Investigators (PIs) and the development of internal data release forms and a user pledge. Phase 2 implemented these processes broadly and produced four codebooks to facilitate user understanding of metadata without extensive staff assistance. The system governed access to four major datasets: the Safety Pilot Model Deployment (SPMD), the Ann Arbor Connected Vehicle Test Environment (AACVTE), and the Integrated Vehicle-Based Safety Systems (IVBSS) Light Vehicle and Heavy Truck Field Operational Tests. These datasets contain real-world kinematic data, video, and Vehicle-to-Vehicle (V2V) communication logs. The access protocol required requestors to complete responsible research training, obtain current Institutional Review Board (IRB) approval for secondary use, and submit formal requests reviewed by the data management committee. Access was granted via secure server login or sanitized data extracts, with strict tracking of access duration and attribution. From September 2017 to March 2020, the new infrastructure facilitated access for 39 requestors, including four external institutions such as Michigan Tech and Chalmers University. The process resulted in the provision of 16 distinct datasets or subsets and supported at least 12 publications. Two requests were denied, primarily due to insufficient IRB protections for secondary data use. The system successfully standardized the evaluation of requests, reduced the technical burden on faculty through codebooks, and ensured privacy compliance through rigorous oversight and temporary access controls. The significance of this work lies in its demonstration of a viable model for managing sensitive, high-value transportation data. It establishes that robust data governance, including clear consent protocols, metadata documentation, and committee-based review, can enable widespread secondary research use while maintaining strict privacy standards. The report highlights ongoing challenges, particularly the lack of dedicated funding for data curation and the difficulty of tracking long-term attribution, suggesting that future sustainable models may require user fees or dedicated institutional support.
Key finding
The implemented data access process provided access to 39 different requestors, resulting in 16 different datasets and at least 12 publications.
Methodology
dataset
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 | partial | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified_with_issues.
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, tool software