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.
@article{arxiv.2503.12820,
title = {Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation},
author = {Kailin Li and Zhenxin Li and Shiyi Lan and Yuan Xie and Zhizhong Zhang and Jiayi Liu and Zuxuan Wu and Zhiding Yu and Jose M. Alvarez},
journal= {arXiv preprint arXiv:2503.12820},
year = {2025}
}