用规划模型教端到端自动驾驶学多模式决策，撞车率降50%
DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model
- 用结构化场景规划模型做教师，生成多目标学习信号
- 在nuScenes和NAVSIM上碰撞率减少50%，闭环性能提升3点
- 适合研究自动驾驶决策与知识蒸馏的学者或工程师
端到端自动驾驶近年发展迅速，但现有方法过度关注本车状态，缺乏以规划为导向的理解，制约了决策鲁棒性。本文提出DistillDrive，一种基于知识蒸馏的端到端自动驾驶模型，通过多样化实例模仿增强多模式运动特征学习。具体而言，采用基于结构化场景表示的规划模型作为教师模型，利用其多样化的规划实例作为端到端模型的多目标学习目标。同时，结合强化学习优化状态到决策的映射，并使用生成建模构建面向规划的实例，促进潜在空间内复杂交互。在nuScenes和NAVSIM数据集上验证，相比基线模型，碰撞率降低50%，闭环性能提升3点。代码与模型已公开于https://github.com/YuruiAI/DistillDrive。
原文摘要 · Abstract (English)
End-to-end autonomous driving has been recently seen rapid development, exerting a profound influence on both industry and academia. However, the existing work places excessive focus on ego-vehicle status as their sole learning objectives and lacks of planning-oriented understanding, which limits the robustness of the overall decision-making prcocess. In this work, we introduce DistillDrive, an end-to-end knowledge distillation-based autonomous driving model that leverages diversified instance imitation to enhance multi-mode motion feature learning. Specifically, we employ a planning model based on structured scene representations as the teacher model, leveraging its diversified planning instances as multi-objective learning targets for the end-to-end model. Moreover, we incorporate reinforcement learning to enhance the optimization of state-to-decision mappings, while utilizing generative modeling to construct planning-oriented instances, fostering intricate interactions within the latent space. We validate our model on the nuScenes and NAVSIM datasets, achieving a 50\% reduction in collision rate and a 3-point improvement in closed-loop performance compared to the baseline model. Code and model are publicly available at https://github.com/YuruiAI/DistillDrive
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。