Exploratory Advanced Research (EAR) Program: Compendium of Papers from Funded Research Projects
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 document serves as a compendium summarizing the outcomes of the Federal Highway Administration’s Exploratory Advanced Research (EAR) Program, highlighting funded projects across behavioral economics, computer vision, materials science, and artificial intelligence. The primary motivation for these studies is to enhance transportation safety, mobility, and infrastructure sustainability through advanced data analytics and novel material applications. A significant portion of the research focuses on leveraging computer vision and machine learning to analyze naturalistic driving data, particularly from the Strategic Highway Research Program 2 Naturalistic Driving Study (SHRP 2 NDS). Researchers at the University of Michigan developed algorithms to detect high-level driver and pedestrian behaviors, such as cellphone use, by linking primitive actions to complex behaviors using bottom-up and top-down machine-learning approaches. Iowa State University and collaborators created the “Deep InSight” platform, utilizing recurrent neural networks to estimate driver states from multi-sensor inputs, addressing challenges like extreme-angle face detection. Similarly, the Virginia Tech Transportation Institute developed deep neural networks to automatically annotate over one million hours of SHRP 2 video data, facilitating the identification of work zones, driver gaze, and in-vehicle occupants. The Volpe National Transportation Systems Center and Oak Ridge National Laboratory contributed tools for detecting roadway features, such as work zones and traffic signals, and established calibration techniques and privacy-preserving methods for video data analysis. In the realm of behavioral economics, Texas A&M University investigated how cognitive biases, such as loss aversion, influence managed lane choices. The study aims to integrate these insights into travel demand models to improve the accuracy of predicting traveler behavior and inform policy decisions through “nudges.” The compendium also details advancements in concrete materials. Addressing the declining supply of traditional fly ash, researchers at UCLA, Purdue University, and Oklahoma State University explored alternative supplementary cementitious materials, including reclaimed fly ash, natural pozzolans, and calcined clays. These projects utilized machine learning and mechanistic modeling to predict the performance, durability, and strength of concrete made with these heterogeneous materials, providing state departments of transportation with data-driven specifications for sustainable infrastructure. Finally, several projects addressed intelligent transportation systems and mixed-autonomy traffic. Researchers at UC Berkeley, the University of Florida, and the University of Texas at Austin developed cyber-physical systems for traffic signal control, cooperative perception, and reservation-based intersection management using augmented reality for human drivers. Additional studies by the University of Wisconsin-Madison and Rutgers University examined human trust in automation and the safety implications of micromobility growth, respectively. Collectively, these findings provide the transportation field with enhanced analytical tools, sustainable material guidelines, and advanced strategies for managing complex, mixed-mode traffic environments.
Key finding
The compendium documents the successful development of various computational tools, behavioral models, and material characterization methods across multiple transportation research domains funded by the EAR Program.
Methodology
mixed_methods
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 (16 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 | 13 | 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
- Theoretical Contribution: computational model