Perception Sharing for Cooperative Driving Automation (CDA) Using Sensor-Data-Sharing Messages [fact sheet]

NHTSA · 2026 · ROSA P / United States. Federal Highway Administration. Office of Safety and Operations Research and Development

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 challenge of pedestrian and bicyclist fatalities at signalized intersections, which account for approximately 20% of all traffic deaths. Limited lines of sight and blind spots often prevent drivers and automated vehicles from detecting vulnerable road users. To mitigate these risks, the document explores Cooperative Driving Automation (CDA) and Cooperative Perception (CP) technologies. These systems enhance situational awareness by sharing location data derived from vehicle and roadside sensors, enabling automated vehicles to assess hazards and execute avoidance maneuvers even when direct visual detection is obstructed. The research methodology combined simulation and live demonstration to validate the efficacy of Sensor-Data-Sharing Messages (SDSMs) based on the SAE J3224 standard. Simulations were conducted using CDASim, a tool integrating the CARMA Platform for vehicle control, CARMA Streets for infrastructure, V2X Hub for communications, and CARLA for realistic environmental rendering. The simulated scenario involved a pedestrian hidden from view by large delivery trucks, testing whether a C-ADS-equipped vehicle could detect the pedestrian via infrastructure-broadcast SDSMs. Following simulation, the technology was demonstrated in real vehicles at the 2025 ITS World Congress in Atlanta, Georgia, involving over 500 industry participants. The results demonstrated significant improvements in collision avoidance and vehicle control. In simulation, the CP approach achieved up to a 98% reduction in pedestrian collisions for the specific test scenarios and smoothed yielding trajectories in most runs. During the live demonstration, an infrastructure-mounted camera detected a pedestrian crossing in front of an emergency response vehicle. This detection was transmitted via a roadside unit to a nearby C-ADS-equipped vehicle, which successfully received the real-time SDSM data and automatically yielded to the pedestrian despite having no direct line of sight. The demonstration compared scenarios with and without CDA to highlight the technology’s ability to prevent collisions in obstructed-view conditions. The findings indicate that CDA and CP technologies can significantly enhance safety by providing automated vehicles with a more complete understanding of the intersection environment. This enhanced perception supports better path planning and automated responses, reducing reliance on direct visual lines of sight. The document outlines future work to expand testing across varied roadway geometries and traffic conditions, evaluate performance under varying latency and sensor error conditions, and advance interoperability standards with industry stakeholders. These steps aim to transition the technology from demonstration to deployment-ready solutions, ensuring CDA meets real-world operational needs and integrates effectively with infrastructure owner-operators.

Key finding

Cooperative perception using sensor-data-sharing messages achieved up to a 98-percent reduction in pedestrian collisions in simulations and enabled successful automated yielding in live demonstrations despite obstructed views.

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 (5 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.

• v2x connected vehicle