Smart, Green, Equitable, Safe, Complete Streets for All - Phase I: Development of a CAV Testbed-enhanced Smart Campus at Morgan State University
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 Phase I of a project to develop a Connected and Autonomous Vehicle (CAV) testbed at Morgan State University, aimed at enhancing road safety for vulnerable road users (VRUs) such as pedestrians and cyclists. The research addresses the need for controlled environments to validate CAV technologies, specifically focusing on sensor accuracy, real-time communication protocols, and conflict detection. The study investigates five key areas: validating LiDAR data against Closed-Circuit Television (CCTV) systems, reviewing national CAV testbeds, assessing real-time communication between Roadside Units (RSUs) and Onboard Units (OBUs), leveraging LiDAR for jaywalking detection, and identifying vehicle-to-pedestrian (V2P) conflicts. The Morgan State University testbed, implemented in April 2022, is equipped with two RSUs, two OBUs, two LiDAR sensors, and four CCTV cameras operating under Cellular-Vehicle-To-Everything (C-V2X) technology at two signalized intersections. To validate sensor performance, researchers compared LiDAR and CCTV data collected over two-hour peak traffic intervals under sunny, rainy, and snowy conditions. Data analysis utilized machine learning algorithms, including Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), for object classification, and Bland-Altman analysis to assess agreement between datasets. Additionally, the study reviewed 70 operational and 101 planned CAV testbeds across the United States to contextualize the Morgan State initiative. To evaluate communication effectiveness, thirty-two participants drove vehicles equipped with OBUs through the testbed, receiving static safety messages regarding pedestrian and bicyclist hazards. Results indicated that LiDAR sensors provided superior accuracy and consistency compared to CCTV cameras, particularly in adverse weather. During snowfall, CCTV reliability decreased significantly due to visibility issues, whereas LiDAR maintained minimal discrepancies in vehicle counts. In rainy conditions, CCTV struggled with lens obstructions, while LiDAR performance remained stable. Sunny conditions yielded minor discrepancies for both systems, though LiDAR remained more dependable due to its immunity to lighting variations. The national review highlighted diverse geographic applications of CAV testbeds, ranging from urban congestion reduction to rural emergency response, utilizing technologies like DSRC and C-V2X. The driver study demonstrated that real-time RSU-to-OBU communication successfully broadcasted safety messages, allowing for the assessment of driver behavioral changes, such as speed reduction and lane positioning, in response to VRU warnings. The significance of this work lies in establishing a robust framework for integrating advanced sensors and communication systems to improve urban traffic safety. By demonstrating the reliability of LiDAR in challenging environments and the efficacy of real-time warning systems, the study supports the development of safer interactions between CAVs, conventional vehicles, and VRUs. The findings provide evidence-based recommendations for infrastructure design and traffic management strategies, contributing to the broader goal of creating smart, equitable, and safe transportation networks. This testbed serves as a critical proving ground for refining CAV functions before widespread public deployment.
Key finding
LiDAR sensors demonstrated superior accuracy and reliability compared to CCTV cameras for traffic monitoring across varying weather conditions, while real-time RSU-to-OBU communication successfully delivered safety messages to drivers in a controlled testbed environment.
Methodology
field_study
Sample size: 32
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: crash risk outcomes, observational prevalence
- Methodological Resource: dataset resource