RounD-KITTI: Merging Realistic Traffic Behavior with KITTI-Calibrated Sensors in CARLA
Résumé
Evaluating autonomous vehicle performance in complex traffic scenarios requires both calibrated sensors and realistic traffic conditions. However, existing traffic datasets focus on vehicle trajectories but lack comprehensive sensor data, while perception datasets provide sensor data but offer limited traffic diversity. To bridge this gap, we introduce an open-source toolset that generates perception datasets in CARLA by embedding realworld vehicle trajectories within a simulated sensor environment. This approach produces sensor data that accurately mirrors real-world traffic dynamics, providing a valuable resource for testing AI-driven autonomous systems in complex scenarios such as roundabouts, where sensor-based perception is essential for safe AV navigation.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |