CVLGRODec 20, 2020

Learning to Localize Using a LiDAR Intensity Map

arXiv:2012.10902v199 citations
AI Analysis

This system addresses the problem of accurate and real-time self-localization for self-driving cars, offering a robust solution for a critical component of autonomous navigation.

This paper proposes a real-time localization system for self-driving cars that learns to embed LiDAR sweeps and intensity maps into a joint deep embedding space. The system achieves centimeter-level accuracy and operates at 15Hz across various LiDAR sensors and environments.

In this paper we propose a real-time, calibration-agnostic and effective localization system for self-driving cars. Our method learns to embed the online LiDAR sweeps and intensity map into a joint deep embedding space. Localization is then conducted through an efficient convolutional matching between the embeddings. Our full system can operate in real-time at 15Hz while achieving centimeter level accuracy across different LiDAR sensors and environments. Our experiments illustrate the performance of the proposed approach over a large-scale dataset consisting of over 4000km of driving.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes