loading page

FMCW Radar on LiDAR Map Localization in Structual Urban Environments
  • +4
  • Yukai Ma,
  • Han Li,
  • Xiangrui Zhao,
  • Yaqing Gu,
  • Xiaolei Lang,
  • Laijian Li,
  • Yong Liu
Yukai Ma
Zhejiang University Institute of Cyber-Systems and Control
Author Profile
Han Li
Zhejiang University Institute of Cyber-Systems and Control
Author Profile
Xiangrui Zhao
Zhejiang University Institute of Cyber-Systems and Control
Author Profile
Yaqing Gu
Zhejiang University Institute of Cyber-Systems and Control
Author Profile
Xiaolei Lang
Zhejiang University Institute of Cyber-Systems and Control
Author Profile
Laijian Li
Zhejiang University Institute of Cyber-Systems and Control
Author Profile
Yong Liu
Zhejiang University Institute of Cyber-Systems and Control

Corresponding Author:[email protected]

Author Profile

Abstract

Multi-sensor fusion-based localization technology has achieved high accuracy in autonomous systems. How to improve the robustness is the main challenge at present. The most commonly used LiDAR and camera are weather-sensitive, while the FMCW Radar has strong adaptability but suffers from noise and ghost effects. In this paper, we propose a heterogeneous localization method called Radar on LiDAR Map (RoLM), which aims to enhance localization accuracy without relying on loop closures by mitigating the accumulated error in Radar odometry in real time. Our approach involves embedding the data from both Radar and LiDAR sensors into a density map. We calculate the spatial vector similarity with an offset to determine the corresponding place index within the candidate map and estimate the rotation and translation. To refine the alignment, we utilize the Iterative Closest Point (ICP) algorithm to achieve optimal matching on the LiDAR submap. We conducted extensive experiments on the Mulran Radar Dataset, Oxford Radar RobotCar Dataset, and our dataset to demonstrate the feasibility and effectiveness of our proposed approach.
10 Jun 2023Submitted to Journal of Field Robotics
10 Jun 2023Submission Checks Completed
10 Jun 2023Assigned to Editor
12 Jun 2023Review(s) Completed, Editorial Evaluation Pending
23 Jun 2023Reviewer(s) Assigned
19 Aug 2023Editorial Decision: Revise Major
19 Oct 20231st Revision Received
19 Oct 2023Submission Checks Completed
19 Oct 2023Assigned to Editor
19 Oct 2023Review(s) Completed, Editorial Evaluation Pending
20 Oct 2023Reviewer(s) Assigned