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.
@article{arxiv.2311.04079,
title = {Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Maps},
author = {Katie Z Luo and Xinshuo Weng and Yan Wang and Shuang Wu and Jie Li and Kilian Q Weinberger and Yue Wang and Marco Pavone},
journal= {arXiv preprint arXiv:2311.04079},
year = {2023}
}