Radar-on-Lidar: metric radar localization on prior lidar maps

Abstract

Radar and lidar, provided by two different range sensors, each has pros and cons of various perception tasks on mobile robots or autonomous driving. In this paper, a Monte Carlo system is used to localize the robot with a rotating radar sensor on 2D lidar maps. We first train a conditional generative adversarial network to transfer raw radar data to lidar data, and achieve reliable radar points from generator. Then an efficient radar odometry is included in the Monte Carlo system. Combining the initial guess from odometry, a measurement model is proposed to match the radar data and prior lidar maps for final 2D positioning. We demonstrate the effectiveness of the proposed localization framework on the public multi-session dataset. The experimental results show that our system can achieve high accuracy for long-term localization in outdoor scenes.

7 pages, 4 figures. This paper has won the Best Conference Paper Award in 2020 IEEE International Conference on Real-time Computing and Robotics (RCAR). A supplementary video is available at https://youtu.be/wE-DbaCDbsU

Cited by in corpus (6)

• Lidar-level localization with radar? The CFEAR approach to accurate, fast and robust large-scale radar odometry in diverse environments
• RaLL: End-to-end Radar Localization on Lidar Map Using Differentiable Measurement Model
• Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning
• Landmark-based Vehicle Self-Localization Using Automotive Polarimetric Radars
• Scalable Radar-based Roadside Perception: Self-localization and Occupancy Heat Map for Traffic Analysis
• CoFi: Coarse-to-Fine ICP for LiDAR Localization in an Efficient Long-lasting Point Cloud Map