ITSC 2025 Paper Abstract

Paper TH-EA-T27.2

Han, Xu (University of California, Los Angeles), Ma, Jiaqi (University of California, Los Angeles)

Leading Urban Traffic Streams with OpenCDA: Distributed Tests Amid CDA Agent Heterogeneity

Scheduled for presentation during the Regular Session "S27b-Safety and Risk Assessment for Autonomous Driving Systems" (TH-EA-T27), Thursday, November 20, 2025, 13:50−14:10, Broadbeach 3

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords Autonomous Vehicle Safety and Performance Testing, Cooperative Driving Systems and Vehicle Coordination in Multi-vehicle Scenarios, Real-world ITS Pilot Projects and Field Tests

Abstract

Distributed testing enables Cooperative Driving Automation (CDA) systems to evaluate interactions among heterogeneous agents in real time across geographically separated sites. Although distributed testing offers realistic assessments, large-scale demonstrations involving multiple participants had not been achieved until now. This paper presents UCLA’s OpenCDA framework, which participated in a distributed test under the VOICES initiative, coordinating with seven other organizations through real-time interactions among independently controlled heterogeneous agents. OpenCDA manages a simulated leading vehicle and improves downstream traffic performance at both the system and individual vehicle levels. Performance gains are validated through analyses of vehicle behavior, traffic stream efficiency, and energy consumption, while the VOICES system’s functionality, interoperability, and scalability are demonstrated through distributed tests in complex urban driving scenarios.