Radar SLAM: A Robust SLAM System for All Weather Conditions

Abstract

A Simultaneous Localization and Mapping (SLAM) system must be robust to support long-term mobile vehicle and robot applications. However, camera and LiDAR based SLAM systems can be fragile when facing challenging illumination or weather conditions which degrade their imagery and point cloud data. Radar, whose operating electromagnetic spectrum is less affected by environmental changes, is promising although its distinct sensing geometry and noise characteristics bring open challenges when being exploited for SLAM. This paper studies the use of a Frequency Modulated Continuous Wave radar for SLAM in large-scale outdoor environments. We propose a full radar SLAM system, including a novel radar motion tracking algorithm that leverages radar geometry for reliable feature tracking. It also optimally compensates motion distortion and estimates pose by joint optimization. Its loop closure component is designed to be simple yet efficient for radar imagery by capturing and exploiting structural information of the surrounding environment. Extensive experiments on three public radar datasets, ranging from city streets and residential areas to countryside and highways, show competitive accuracy and reliability performance of the proposed radar SLAM system compared to the state-of-the-art LiDAR, vision and radar methods. The results show that our system is technically viable in achieving reliable SLAM in extreme weather conditions, e.g. heavy snow and dense fog, demonstrating the promising potential of using radar for all-weather localization and mapping.

Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys

“…In addition, researchers have to spend lots of time and effort to maintain and repair LiDARs installed on the IVs. 4) Fusion-based SLAM: In order to avoid the problems with failures in single sensor or low robustness, fusing multiple modalities data methods have been introduced by researchers including visual-inertial [22][23][24], LiDAR-inertial [25][26][27][28], visual-LiDAR inertial [29][30][31] and other fusion, such as adding sonars [32] or radars [33], SLAM approaches. We found that fusion methods usually introduce IMU data with higher updating frequency to SLAM systems.…”

Radio SLAM for 6G Systems at THz Frequencies: Design and Experimental Validation

“…Surveys on the general SLAM problem can be found in [11], [13], which provide an overview of various techniques, including FastSLAM, GraphSLAM, and belief propagation SLAM [15], [26]- [28]. Initially, R-SLAM was predominantly employed in radar and automotive niche applications [29]- [31]. For instance, in [29], an algorithm utilizing the iterative closest point (ICP) graph method is presented, which matches consecutive scans obtained from a frequency-modulated continuouswave (FMCW) radar along with odometry information.…”

FMCW Radar on LiDAR map localization in structural urban environments

“…Although Radar has its drawbacks, including multipath phenomena, ghost reflections, higher noise levels, and lower accuracy compared to LiDAR, it demonstrates exceptional robustness and is capable of long-range detection and map construction during severe weather conditions. Research in this area has gained significant attention in recent years (Hong et al, 2020(Hong et al, , 2021.…”