HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps

TL;DR

HDMapGen is a hierarchical graph generative model that creates diverse, high-quality HD maps efficiently, addressing data scarcity for autonomous driving systems by enabling the generation of realistic road topologies.

Contribution

This work introduces HDMapGen, a novel hierarchical graph model for HD map generation, improving quality, diversity, and scalability over existing methods.

Findings

HDMapGen outperforms baseline methods on Argoverse and in-house datasets.

The model achieves high scalability and efficiency.

Generated maps are diverse and realistic, aiding autonomous driving development.

Abstract

High Definition (HD) maps are maps with precise definitions of road lanes with rich semantics of the traffic rules. They are critical for several key stages in an autonomous driving system, including motion forecasting and planning. However, there are only a small amount of real-world road topologies and geometries, which significantly limits our ability to test out the self-driving stack to generalize onto new unseen scenarios. To address this issue, we introduce a new challenging task to generate HD maps. In this work, we explore several autoregressive models using different data representations, including sequence, plain graph, and hierarchical graph. We propose HDMapGen, a hierarchical graph generation model capable of producing high-quality and diverse HD maps through a coarse-to-fine approach. Experiments on the Argoverse dataset and an in-house dataset show that HDMapGen significantly outperforms baseline methods. Additionally, we demonstrate that HDMapGen achieves high scalability and efficiency.