GlobalMapNet: An Online Framework for Vectorized Global HD Map Construction

TL;DR

GlobalMapNet is an innovative online framework that constructs vectorized high-definition maps for autonomous driving by integrating local maps into a consistent global map, leveraging crowdsourcing and online mapping techniques.

Contribution

It introduces the first online framework for vectorized global HD map construction, combining local map matching, merging, and historical data fusion for consistency.

Findings

Successfully generates globally consistent HD maps on Argoverse2 and nuScenes datasets.

Outperforms existing methods in map accuracy and consistency.

Efficiently updates maps in real-time during vehicle operation.

Abstract

High-definition (HD) maps are essential for autonomous driving systems. Traditionally, an expensive and labor-intensive pipeline is implemented to construct HD maps, which is limited in scalability. In recent years, crowdsourcing and online mapping have emerged as two alternative methods, but they have limitations respectively. In this paper, we provide a novel methodology, namely global map construction, to perform direct generation of vectorized global maps, combining the benefits of crowdsourcing and online mapping. We introduce GlobalMapNet, the first online framework for vectorized global HD map construction, which updates and utilizes a global map on the ego vehicle. To generate the global map from scratch, we propose GlobalMapBuilder to match and merge local maps continuously. We design a new algorithm, Map NMS, to remove duplicate map elements and produce a clean map. We also propose GlobalMapFusion to aggregate historical map information, improving consistency of prediction. We examine GlobalMapNet on two widely recognized datasets, Argoverse2 and nuScenes, showing that our framework is capable of generating globally consistent results.