发表机构
University of Toronto; ETH Zürich（多伦多大学; 苏黎世联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Dr-LiSA 提出一种直接配准方法，利用学习的前向模型将 2D 雷达扫描与 3D 激光雷达地图在 $SE(3)$ 中对齐，克服模态差异，在 90 公里数据上优于现有雷达-激光雷达方法，平面精度媲美雷达-雷达系统。
AI 中文摘要
本文介绍了 Dr-LiSA，这是一种首创的直接方法，用于在 $SE(3)$ 中针对 3D 激光雷达地图定位 2D 旋转雷达强度测量。雷达-激光雷达定位结合了两种传感模态的互补优势：雷达对恶劣天气和降水具有鲁棒性，而激光雷达在有利条件下提供高保真 3D 地图。然而，现有的雷达-激光雷达定位方法仅限于平面 $SE(2)$ 定位，并且通常未能达到激光雷达-激光雷达甚至雷达-雷达系统所实现的精度。一个关键挑战是雷达和激光雷达之间巨大的传感模态差距，它们以根本不同的方式观察和表示场景结构。Dr-LiSA 通过学习的前向模型弥合了这一差距，该模型从候选位姿处的激光雷达子地图预测雷达测量值，从而能够在 $SE(3)$ 中直接光度配准预测和观测的雷达扫描。Dr-LiSA 在 $SE(2)$ 中优于先前的雷达-激光雷达方法，同时在超过 90 公里的道路数据上实现了与最先进的雷达-雷达定位相当的平面精度。
英文摘要
This paper introduces Dr-LiSA, a first-of-its-kind direct method for localizing 2D spinning radar intensity measurements in $SE(3)$ against 3D lidar maps. Radar-lidar localization combines the complementary strengths of the two sensing modalities: radar is robust to adverse weather and precipitation, while lidar provides high-fidelity 3D maps in favourable conditions. However, existing radar-lidar localization methods are restricted to planar $SE(2)$ localization and have generally fallen short of the accuracy achieved by lidar-lidar and even radar-radar systems. A key challenge is the substantial sensing-modality gap between radar and lidar, which observe and represent scene structure in fundamentally different ways. Dr-LiSA bridges this gap using a learned forward model that predicts radar measurements from a lidar submap at a candidate pose, enabling direct photometric alignment of predicted and observed radar scans in $SE(3)$. Dr-LiSA outperforms prior radar-lidar approaches in $SE(2)$ while achieving planar accuracy competitive with state-of-the-art radar-radar localization across more than 90 km of on-road data.
Comments8 pages, 6 figures, paper under review
