Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation
This addresses safety issues in autonomous driving systems, though it appears incremental as it builds on existing distillation approaches with expanded metrics.
The paper tackles the problem of unsafe behaviors in end-to-end autonomous driving by introducing Hydra-MDP++, a teacher-student knowledge distillation framework that learns from human demonstrations and rule-based experts, achieving a 91.0% drive score on NAVSIM.
Hydra-MDP++ introduces a novel teacher-student knowledge distillation framework with a multi-head decoder that learns from human demonstrations and rule-based experts. Using a lightweight ResNet-34 network without complex components, the framework incorporates expanded evaluation metrics, including traffic light compliance (TL), lane-keeping ability (LK), and extended comfort (EC) to address unsafe behaviors not captured by traditional NAVSIM-derived teachers. Like other end-to-end autonomous driving approaches, \hydra processes raw images directly without relying on privileged perception signals. Hydra-MDP++ achieves state-of-the-art performance by integrating these components with a 91.0% drive score on NAVSIM through scaling to a V2-99 image encoder, demonstrating its effectiveness in handling diverse driving scenarios while maintaining computational efficiency.