Enhancing Vulnerable Road User Safety at Signalized Intersections Through Cooperative Perception and Driving Automation: 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 addresses the critical need to enhance safety for vulnerable road users (VRUs), such as pedestrians and cyclists, at signalized intersections. Despite overall declines in transportation fatalities, VRU fatality rates continue to rise, with intersections accounting for a disproportionate share of pedestrian and bicyclist crashes. The study investigates the potential of Cooperative Perception (CP) technology to mitigate these risks by leveraging communication between roadside infrastructure and vehicles. The primary objective was to develop and evaluate a CP VRU safety application within the Federal Highway Administration’s (FHWA) open-source CARMA Ecosystem, aiming to improve situational awareness and enable proactive collision avoidance for Cooperative Automated Driving System (C-ADS)-equipped vehicles. The research team developed a CP application that fuses data from infrastructure sensors (e.g., cameras on signal poles) and vehicle sensors. Infrastructure detects VRUs, including those occluded from the vehicle’s line of sight, and broadcasts this information via Sensor Data Sharing Messages (SDSMs). The C-ADS-equipped vehicle uses this data to adjust its trajectory in real-time. Testing was conducted in CDASim, an everything-in-the-loop simulation environment integrating the CARMA Platform, traffic simulators, and communication simulators. The experimental design included four primary situations (straight-through and left-turn maneuvers, with and without CP), expanded into eight specific scenarios by varying vehicle and VRU speeds. Each scenario was repeated three times, resulting in 48 test runs with CP enabled and 48 without, under ideal conditions with no communication latency or packet loss. The results demonstrated significant safety improvements. In the baseline scenarios without CP, crashes occurred in 100% of the 48 test runs. In contrast, the CP-enabled scenarios prevented crashes in 98% of the 48 runs, with only one collision occurring. This high avoidance rate highlights the effectiveness of infrastructure-to-vehicle communication in detecting occluded VRUs and enabling timely interventions. The study also analyzed performance metrics such as message frequency, positional error, and vehicle deceleration profiles, confirming that the system allowed vehicles to react appropriately to VRU presence. The findings suggest that CP technology can play a pivotal role in advancing the U.S. Department of Transportation’s Vision Zero goal of eliminating traffic fatalities. By providing comprehensive environmental awareness beyond individual vehicle sensor limitations, CP enhances safety for all road users within communication range. However, the authors note that results were derived from controlled simulations with ideal conditions. Future work must address real-world challenges, including weather variability, communication disruptions, and complex traffic patterns. The report recommends expanding testing to physical environments and refining algorithms to ensure robustness, emphasizing that CP should be integrated into broader safety strategies involving infrastructure improvements and public education.
Key finding
The cooperative perception application prevented crashes in 98 percent of simulation test runs compared to a baseline scenario without the application.
Methodology
simulator
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
- Methodological Resource: tool software, dataset resource