用人类示范和规则专家训练驾驶模型，提升安全与舒适性。
Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation
- 多头解码器融合人类示范与规则专家指导知识
- 在NAVSIM上达91.0%驾驶得分，显著提升安全行为表现
- 轻量网络设计，适合实际部署，兼顾效率与性能
Hydra-MDP++ 提出一种新型教师-学生知识蒸馏框架，采用多头解码器，从人类示范和基于规则的专家中学习。该框架使用轻量级 ResNet-34 网络，不依赖复杂组件，引入扩展评估指标，包括交通灯遵守率（TL）、车道保持能力（LK）和扩展舒适度（EC），以捕捉传统基于 NAVSIM 的教师未涵盖的不安全行为。与其它端到端自动驾驶方法类似，Hydra-MDP++ 直接处理原始图像，无需依赖特权感知信号。通过扩展至 V2-99 图像编码器，该方法在 NAVSIM 上实现了 91.0% 的驾驶得分，展现出在多样化驾驶场景下的优异表现，同时保持计算高效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。