Miniature Testbed for Validating Multi-Agent Cooperative Autonomous Driving
Hyunchul Bae, Eunjae Lee, Jehyeop Han, Minhee Kang, Jaehyeon Kim, Junggeun Seo, Minkyun Noh, Heejin Ahn
AI summary
Problem
Existing validation platforms for cooperative autonomous driving are either prohibitively expensive full-scale facilities or lack physical realism in simulations, while current miniature testbeds lack active smart infrastructure for true V2X validation.
Approach
The authors designed a 1:15-scale miniature testbed featuring scaled autonomous vehicles and smart roadside infrastructure with 3D LiDAR and edge computing, linked via Wi-Fi to emulate real-world V2X communication.
Key results
- A 1:15-scale testbed integrating autonomous vehicles and active smart infrastructure
- Hardware and software architecture enabling V2V and V2I communication via ROS2 and Wi-Fi
- Infrastructure-based 3D object detection and human-driven vehicle identification pipeline
- Successful intersection management case study coordinating CAVs and HVs under mixed-traffic conditions
Why it matters
It provides researchers and engineers with a cost-effective, physically realistic platform to develop and validate cooperative driving algorithms and V2X protocols before costly full-scale deployment.
Abstract
Cooperative autonomous driving, which extends vehicle autonomy by enabling real-time collaboration between vehicles and smart roadside infrastructure, remains a challenging yet essential problem. However, none of the existing testbeds employ smart infrastructure equipped with sensing, edge computing, and communication capabilities. To address this gap, we design and implement a 1:15-scale miniature testbed, CIVAT, for validating cooperative autonomous driving, consisting of a scaled urban map, autonomous vehicles with onboard sensors, and smart infrastructure. The proposed testbed integrates V2V and V2I communication with the publish-subscribe pattern through a shared Wi-Fi and ROS2 framework, enabling information exchange between vehicles and infrastructure to realize cooperative driving functionality. As a case study, we validate the system through infrastructure-based perception and intersection management experiments.