DriveE2E: Closed-Loop Benchmark for End-to-End Autonomous Driving through Real-to-Simulation
This provides a more realistic evaluation framework for autonomous driving researchers, though it is incremental as it builds on existing simulation tools.
The paper tackles the problem of unrealistic closed-loop evaluation for end-to-end autonomous driving by introducing a benchmark that integrates real-world traffic scenarios into the CARLA simulator, using 800 dynamic scenarios from 100 hours of video and digital twins of 15 intersections to improve realism.
Closed-loop evaluation is increasingly critical for end-to-end autonomous driving. Current closed-loop benchmarks using the CARLA simulator rely on manually configured traffic scenarios, which can diverge from real-world conditions, limiting their ability to reflect actual driving performance. To address these limitations, we introduce a simple yet challenging closed-loop evaluation framework that closely integrates real-world driving scenarios into the CARLA simulator with infrastructure cooperation. Our approach involves extracting 800 dynamic traffic scenarios selected from a comprehensive 100-hour video dataset captured by high-mounted infrastructure sensors, and creating static digital twin assets for 15 real-world intersections with consistent visual appearance. These digital twins accurately replicate the traffic and environmental characteristics of their real-world counterparts, enabling more realistic simulations in CARLA. This evaluation is challenging due to the diversity of driving behaviors, locations, weather conditions, and times of day at complex urban intersections. In addition, we provide a comprehensive closed-loop benchmark for evaluating end-to-end autonomous driving models. Project URL: \href{https://github.com/AIR-THU/DriveE2E}{https://github.com/AIR-THU/DriveE2E}.