Radar-based Pose Optimization for HD Map Generation from Noisy Multi-Drive Vehicle Fleet Data
🤖 AI Summary
This work addresses the degradation of high-definition map accuracy caused by localization noise from low-cost vehicle-mounted sensors. To enhance global pose consistency across fleet-collected data, the authors propose a novel method that integrates multi-pass LiDAR point cloud registration with pose graph optimization. For the first time, raw LiDAR point cloud alignment is tightly coupled with pose graph refinement, effectively mitigating error accumulation and enabling the construction of high-fidelity LiDAR occupancy maps and lane boundary maps. Experimental results demonstrate that the generated maps clearly resolve high-contrast structures such as guardrail posts and significantly outperform conventional line-based lane detection approaches in representing lane boundaries, offering a promising new pathway for cost-effective high-definition mapping.
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
HD map generation
localization noise
multi-drive data
radar-based pose optimization
autonomous driving
Innovation
Methods, ideas, or system contributions that make the work stand out.
radar-based pose optimization
pose graph optimization
HD map generation
multi-drive alignment
radar occupancy map
🔎 Similar Papers
No similar papers found.
