Neural HD Map Generation from Multiple Vectorized Tiles Locally Produced by Autonomous Vehicles

TL;DR

This paper introduces GNMap, an end-to-end neural network that constructs high-definition maps from multiple locally produced vectorized tiles, improving accuracy and completeness for autonomous driving applications.

Contribution

The paper presents GNMap, a novel neural network architecture that integrates multiple vectorized tiles to generate accurate and complete HD maps, surpassing state-of-the-art methods.

Findings

GNMap achieves over 5% higher F1 score than previous methods.

It effectively combines multiple local map tiles into a coherent global HD map.

Successfully deployed in real-world autonomous driving systems.

Abstract

High-definition (HD) map is a fundamental component of autonomous driving systems, as it can provide precise environmental information about driving scenes. Recent work on vectorized map generation could produce merely 65% local map elements around the ego-vehicle at runtime by one tour with onboard sensors, leaving a puzzle of how to construct a global HD map projected in the world coordinate system under high-quality standards. To address the issue, we present GNMap as an end-to-end generative neural network to automatically construct HD maps with multiple vectorized tiles which are locally produced by autonomous vehicles through several tours. It leverages a multi-layer and attention-based autoencoder as the shared network, of which parameters are learned from two different tasks (i.e., pretraining and finetuning, respectively) to ensure both the completeness of generated maps and the correctness of element categories. Abundant qualitative evaluations are conducted on a real-world dataset and experimental results show that GNMap can surpass the SOTA method by more than 5% F1 score, reaching the level of industrial usage with a small amount of manual modification. We have already deployed it at Navinfo Co., Ltd., serving as an indispensable software to automatically build HD maps for autonomous driving systems.