What Matters for Scalable and Robust Learning in End-to-End Driving Planners?

Researchers introduce BevAD, a new lightweight end-to-end autonomous driving architecture that achieves 72.7% success rate on the Bench2Drive benchmark. The study systematically analyzes architectural patterns in closed-loop driving performance, revealing limitations of open-loop dataset approaches and demonstrating strong data-scaling behavior through pure imitation learning.

• →BevAD achieves 72.7% success rate on Bench2Drive benchmark, outperforming existing end-to-end driving architectures.
• →Research reveals that architectural advances excelling in open-loop datasets often fail in closed-loop driving scenarios.
• →The study systematically examines three key architectural patterns: high-resolution perceptual representations, disentangled trajectory representations, and generative planning.
• →BevAD demonstrates strong data-scaling behavior using pure imitation learning without additional training techniques.
• →The lightweight architecture addresses scalability issues in autonomous driving while maintaining robust performance in interactive scenarios.