Divide and Conquer: A Systematic Approach for Industrial Scale High-Definition OpenDRIVE Generation from Sparse Point Clouds

TL;DR

This paper introduces a scalable, automated method for generating high-definition OpenDRIVE maps from sparse LiDAR point clouds, crucial for advanced driving functions, by processing road segments with minimal external info.

Contribution

A novel scalable approach for large-scale high-definition map generation from sparse data, integrating minimal external info and segment processing for industrial applications.

Findings

Achieves high-definition map accuracy from sparse LiDAR data.

Demonstrates integration of generated maps into driving simulation.

Supports scalable and flexible map creation for industrial use.

Abstract

High-definition road maps play a crucial role in the functionality and verification of highly automated driving functions. These contain precise information about the road network, geometry, condition, as well as traffic signs. Despite their importance for the development and evaluation of driving functions, the generation of high-definition maps is still an ongoing research topic. While previous work in this area has primarily focused on the accuracy of road geometry, we present a novel approach for automated large-scale map generation for use in industrial applications. Our proposed method leverages a minimal number of external information about the road to process LiDAR data in segments. These segments are subsequently combined, enabling a flexible and scalable process that achieves high-definition accuracy. Additionally, we showcase the use of the resulting OpenDRIVE in driving function simulation.