The Role of Artificial Intelligence and Machine Learning in Federally Supported Surface Transportation Initiatives : [brochure]
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 2018 brochure from the Federal Highway Administration (FHWA) outlines the role of artificial intelligence (AI) and machine learning (ML) in federally supported surface transportation initiatives. The document addresses the need to leverage these technologies to improve traffic safety, efficiency, and infrastructure management. It is motivated by the increasing availability of multimodal transportation data and the strategic goals outlined in the National Artificial Intelligence Research and Development Strategic Plan, which prioritizes federal R&D in AI to address long-term technical and societal challenges. The FHWA’s Exploratory Advanced Research (EAR) Program facilitates this research by supporting projects that might not offer immediate returns to private industry. The document details two primary research areas: big data analysis and video analytics. In the big data domain, the Palo Alto Research Center (PARC) developed machine learning tools to integrate disparate datasets, including the Strategic Highway Research Program 2 (SHRP 2) naturalistic driving study, roadway-weather data, and intersection sensor logs. This integration aimed to detect safety issues hidden within isolated data streams. Concurrently, the Calspan-University of Buffalo Research Center (CUBRC) created the Transportation Research Informatics Platform (TRIP), a dashboard that ingests and displays streaming and historical traffic data, such as crashes, volumes, and weather conditions, to identify relationships between variables. In the video analytics domain, researchers analyzed 1.2 million hours of video data from the SHRP 2 naturalistic driving study to establish baselines for high-risk driver behavior. Carnegie Mellon University developed algorithms to parse ambiguous video data, automate the interpretation of driver emotional states, and detect distraction or fatigue. The University of Wisconsin–Madison created an open software platform for quantifying driver distraction and engagement, while SRI International developed the DCode system to extract specific driver behavior features, such as head pose and mobile phone usage. Oak Ridge National Laboratory contributed calibration techniques to assist the broader research community in utilizing this vast dataset. The significance of these efforts lies in their potential to augment structural health monitoring, improve network mobility, and support travelers with disabilities through real-time operational tools. The document concludes that while opportunities for AI and ML in transportation are vast, challenges remain in data validation, privacy protection, and the development of real-time applications. The EAR Program continues to bridge basic and applied research, fostering partnerships across government, academia, and industry to advance transportation safety and efficiency through advanced computational methods.
Key finding
The FHWA EAR Program supports research integrating disparate transportation datasets and automating video analytics to identify safety trends and quantify driver behavior.
Methodology
review
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 (44 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 | 41 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 24 | 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
- Theoretical Contribution: computational model