Perception Sharing for Cooperative Driving Automation (CDA)

NHTSA · 2025 · ROSA P / United States. Department of Transportation. Federal Highway Administration

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 fact sheet addresses the critical safety issue of pedestrian and bicyclist fatalities, which accounted for approximately 21% of all U.S. traffic deaths in 2023. The primary motivation is the limitation of onboard vehicle sensors, which often suffer from blind spots or obstructed sight lines that prevent drivers and automated vehicles from detecting vulnerable road users (VRUs) in time to avoid collisions. The document proposes Cooperative Driving Automation (CDA) as a solution, specifically focusing on cooperative perception. This approach enables vehicles and infrastructure to share location data and object information, thereby enhancing situational awareness beyond the capabilities of individual onboard sensors. To evaluate this concept, the Federal Highway Administration (FHWA) conducted a series of tests using the CARMA cooperative perception system. The experimental design involved vulnerable road user scenarios where a pedestrian walked through a crosswalk at various angles relative to a stationary vehicle. Some test cases included obstructed lines of sight for the vehicle, while others did not. The infrastructure component utilized a roadside unit equipped with a thermal sensor for object detection. Data processing and communication were handled by CARMA Streets and a Vehicle-to-Everything (V2X) Hub. The stationary vehicle, running the CARMA Platform, served as the receiver, processing the incoming data to determine if the pedestrian posed a hazard. Independent evaluators from the Volpe National Transportation Systems Center assessed the system based on consistency, latency, message creation, and the accuracy of position estimates compared to onboard LiDAR data. The results demonstrated that the CARMA cooperative perception system successfully transferred and processed information with an average latency of less than 6.5 milliseconds, measured from the moment of VRU detection to communication with the Cooperative Automated Driving System (C-ADS). This low latency allows the system to make safety decisions rapidly. The evaluation confirmed that infrastructure-based sensors could effectively detect VRUs and transmit Personal Safety Messages (PSMs) that the vehicle’s automated driving system could translate into actionable objects for path planning. The study also highlighted that careful calibration of infrastructure sensors is determinative for system efficacy, noting significant differences in position estimation when comparing infrastructure sensors with onboard LiDAR. The significance of these findings lies in the potential for cooperative perception to improve both safety and mobility. By overcoming visual limitations, CDA applications can enhance collision avoidance and support more effective motion planning for speed and acceleration. The report identifies several next steps for the field, including the need for standardized sensor outputs and uncertainty measures to facilitate effective data fusion. Additionally, the development of standardized sensor application programming interfaces and adaptive communication protocols is recommended to accelerate the deployment of cooperative perception technologies across different vendors and traffic contexts.

Key finding

The CARMA cooperative perception system successfully transferred and processed vulnerable road user detection information in less than 6.5 milliseconds on average, enabling faster safety decisions for automated driving systems.

Methodology

field_study

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).

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.

• situational awareness