MapFM: Foundation Model-Driven HD Mapping with Multi-task Contextual Learning

Leonid Ivanov, Vasily Yuryev, Dmitry Yudin

Abstract: In autonomous driving, high-definition (HD) maps and semantic maps in bird's-eye view (BEV) are essential for accurate localization, planning, and decision-making. This paper introduces an enhanced framework for online HD map generation. We significantly boost feature representation quality by incorporating powerful foundation model for encoding camera images. To further enrich the model's understanding of the environment and improve prediction quality, we integrate auxiliary prediction heads for semantic segmentation and lidar features in the BEV representation. This multi-task learning approach provides richer contextual supervision, leading to a more comprehensive scene representation and ultimately resulting in higher accuracy and improved quality of the predicted vectorized HD maps.