Autonomous driving has traditionally relied heavily on costly and labor-intensive High Definition (HD) maps, hindering scalability. In contrast, Standard Definition (SD) maps are more affordable and have worldwide coverage, offering a scalable alternative. In this work, we systematically explore the effect of SD maps for real-time lane-topology understanding. We propose a novel framework to integrate SD maps into online map prediction and propose a Transformer-based encoder, SD Map Encoder Representations from transFormers, to leverage priors in SD maps for the lane-topology prediction task. This enhancement consistently and significantly boosts (by up to 60%) lane detection and topology prediction on current state-of-the-art online map prediction methods without bells and whistles and can be immediately incorporated into any Transformer-based lane-topology method. Code is available at https://github.com/NVlabs/SMERF.

翻译：自动驾驶传统上严重依赖成本高昂且劳动密集型的高清地图，这阻碍了其可扩展性。相比之下，标准定义地图成本更低且覆盖全球，提供了一种可扩展的替代方案。本文系统研究了标准定义地图对实时车道-拓扑理解的影响。我们提出了一种新颖框架，将标准定义地图集成到在线地图预测中，并设计了一种基于Transformer的编码器——标准定义地图Transformer编码器表示，以利用标准定义地图中的先验信息完成车道-拓扑预测任务。该增强方法无需额外复杂设计，即可持续且显著地提升当前最先进的在线地图预测方法的车道检测与拓扑预测性能（提升幅度高达60%），并可立即集成到任何基于Transformer的车道-拓扑方法中。代码可在https://github.com/NVlabs/SMERF获取。