🤖 AI Summary
This work addresses the absence of a verifiable physical-virtual hybrid platform capable of generating cooperative perception validation evidence compliant with European autonomous driving regulations. The authors present the first mixed vehicle-in-the-loop (ViL) platform integrating real vehicles with CARLA digital twins in a public-road testbed, where V2X communication pipelines couple ETSI CAM/CPM messages to enable runtime fusion into probabilistic occupancy grids. The platform facilitates multi-scenario cooperative perception evaluation and identifies localization noise as the dominant error source. Experimental results demonstrate that cooperative perception substantially extends field-of-view coverage and improves occupancy cell recall; however, under moderate-to-high localization noise, its associated uncertainty surpasses weather effects as the primary performance bottleneck.
📝 Abstract
European safety regulation now permits a large share of automated-driving homologation evidence to be produced virtually, provided a validated physical-virtual facility generates it. We present a deployed hybrid Vehicle-in-the-Loop (ViL) platform that couples a real instrumented vehicle with a CARLA-based digital twin (DT) through a V2X message pipeline, and we report its first integrated operation on a public-road-representative test track. A real vehicle streams ETSI-compliant CAM/CPM messages into the DT, where a GPU-accelerated Cooperative Perception (CP) module fuses them into a probabilistic occupancy grid during scenario runtime. We demonstrate the platform on a multi-vehicle double T-intersection scenario, characterise the CP workload across nominal, rain and night conditions and five localization-noise levels, and discuss the platform's current architectural limits and the engineering targets they define. The results show that CP substantially widens field-of-view (FoV) coverage and improves occupied-cell recall, and that beyond a moderate localization-noise threshold, positioning uncertainty, and not weather, becomes the dominant error source. We outline the platform's trajectory toward a Mediterranean operational design domain (ODD) testing service.