Radar-based Pose Optimization for HD Map Generation from Noisy Multi-Drive Vehicle Fleet Data

TL;DR

This paper presents a radar-based pose optimization method that reduces noise in multi-drive vehicle data to generate accurate HD maps, improving localization and lane boundary mapping for autonomous driving.

Contribution

It introduces a novel approach combining radar point cloud alignment and pose graph optimization to enhance map accuracy from noisy vehicle fleet data.

Findings

Enhanced global radar occupancy maps with clearer feature visibility

Significant improvement in lane boundary map quality

Effective noise mitigation in multi-drive vehicle datasets

Abstract

High-definition (HD) maps are important for autonomous driving, but their manual generation and maintenance is very expensive. This motivates the usage of an automated map generation pipeline. Fleet vehicles provide sufficient sensors for map generation, but their measurements are less precise, introducing noise into the mapping pipeline. This work focuses on mitigating the localization noise component through aligning radar measurements in terms of raw radar point clouds of vehicle poses of different drives and performing pose graph optimization to produce a globally optimized solution between all drives present in the dataset. Improved poses are first used to generate a global radar occupancy map, aimed to facilitate precise on-vehicle localization. Through qualitative analysis we show contrast-rich feature clarity, focusing on omnipresent guardrail posts as the main feature type observable in the map. Second, the improved poses can be used as a basis for an existing lane boundary map generation pipeline, majorly improving map output compared to its original pure line detection based optimization approach.