用16个导航引导的稀疏标记实现端到端自动驾驶，大幅提速且减少碰撞。
Navigation-Guided Sparse Scene Representation for End-to-End Autonomous Driving
- 仅用16个导航引导的稀疏标记表示场景，无需人工标注任务
- 在nuScenes上碰撞率降低51.6%，推理速度提升10.9倍
- 适合追求实时性与可扩展性的自动驾驶系统部署
端到端自动驾驶方法通常依赖于监督感知任务来提取显式场景信息（如物体、地图），这需要昂贵的人工标注，限制了实时应用中的部署与数据扩展性。本文提出SSR框架，仅使用16个导航引导的稀疏标记作为场景表示，高效提取对导航意图至关重要的信息。该方法消除了对人工设计的监督子任务的需求，使计算资源集中于与导航直接相关的要素。我们还引入一个时间增强模块，通过自监督将预测的未来场景与实际未来场景对齐。SSR在nuScenes上实现相对于UniAD的27.2%相对L2误差降低和51.6%碰撞率下降，推理速度提升10.9倍，训练时间快13倍。此外，在CARLA Town05 Long基准上，驾驶评分相比VAD-Base提升48.6分。该框架显著推进了实时自动驾驶系统的进展，为未来可扩展部署铺平道路。代码已开源：https://github.com/PeidongLi/SSR。
原文摘要 · Abstract (English)
End-to-End Autonomous Driving (E2EAD) methods typically rely on supervised perception tasks to extract explicit scene information (e.g., objects, maps). This reliance necessitates expensive annotations and constrains deployment and data scalability in real-time applications. In this paper, we introduce SSR, a novel framework that utilizes only 16 navigation-guided tokens as Sparse Scene Representation, efficiently extracting crucial scene information for E2EAD. Our method eliminates the need for human-designed supervised sub-tasks, allowing computational resources to concentrate on essential elements directly related to navigation intent. We further introduce a temporal enhancement module, aligning predicted future scenes with actual future scenes through self-supervision. SSR achieves a 27.2\% relative reduction in L2 error and a 51.6\% decrease in collision rate to UniAD in nuScenes, with a 10.9$\times$ faster inference speed and 13$\times$ faster training time. Moreover, SSR outperforms VAD-Base with a 48.6-point improvement on driving score in CARLA's Town05 Long benchmark. This framework represents a significant leap in real-time autonomous driving systems and paves the way for future scalable deployment. Code is available at https://github.com/PeidongLi/SSR.
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。