# RadarLCD: Learnable Radar-based Loop Closure Detection Pipeline

arXiv: https://arxiv.org/abs/2309.07094 · HTML: https://mlsanity.com/paper/2309.07094/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 13 Sep 2023.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Visual Transformers: Token-based Image Representation and Processing for Computer Vision](https://mlsanity.com/paper/2006.03677/) (2020)
- [The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset](https://mlsanity.com/paper/1909.01300/) (2019)
- [OverlapNet: Loop Closing for LiDAR-based SLAM](https://mlsanity.com/paper/2105.11344/) (2021)
- [LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM](https://mlsanity.com/paper/2103.05056/) (2021)
- [RSS-Net: Weakly-Supervised Multi-Class Semantic Segmentation with FMCW Radar](https://mlsanity.com/paper/2004.03451/) (2020)
- [Robust Differentiable SVD](https://mlsanity.com/paper/2104.03821/) (2021)
- [Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar](https://mlsanity.com/paper/2001.10789/) (2020)
- [Probably Unknown: Deep Inverse Sensor Modelling In Radar](https://mlsanity.com/paper/1810.08151/) (2018)
- [Kidnapped Radar: Topological Radar Localisation using Rotationally-Invariant Metric Learning](https://mlsanity.com/paper/2001.09438/) (2020)
- [Masking by Moving: Learning Distraction-Free Radar Odometry from Pose Information](https://mlsanity.com/paper/1909.03752/) (2019)
- [Look Around You: Sequence-based Radar Place Recognition with Learned Rotational Invariance](https://mlsanity.com/paper/2003.04699/) (2020)
- [RadarSLAM: Radar based Large-Scale SLAM in All Weathers](https://mlsanity.com/paper/2005.02198/) (2020)
- [PADLoC: LiDAR-Based Deep Loop Closure Detection and Registration Using Panoptic Attention](https://mlsanity.com/paper/2209.09699/) (2022)
- [Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning](https://mlsanity.com/paper/2105.14152/) (2021)
- [A Normal Distribution Transform-Based Radar Odometry Designed For Scanning and Automotive Radars](https://mlsanity.com/paper/2103.07908/) (2021)
- [Radar-only ego-motion estimation in difficult settings via graph matching](https://mlsanity.com/paper/1904.11476/) (2019)
- [TBV Radar SLAM -- trust but verify loop candidates](https://mlsanity.com/paper/2301.04397/) (2023)
- [Keep off the Grass: Permissible Driving Routes from Radar with Weak Audio Supervision](https://mlsanity.com/paper/2005.05175/) (2020)
- [Self-Supervised Localisation between Range Sensors and Overhead Imagery](https://mlsanity.com/paper/2006.02108/) (2020)
- [ART-SLAM: Accurate Real-Time 6DoF LiDAR SLAM](https://mlsanity.com/paper/2109.05483/) (2021)
- [Perception Through 2D-MIMO FMCW Automotive Radar Under Adverse Weather](https://mlsanity.com/paper/2104.01639/) (2021)
- [CFEAR Radarodometry -- Conservative Filtering for Efficient and Accurate Radar Odometry](https://mlsanity.com/paper/2105.01457/) (2021)

## Abstract (arXiv)

Loop Closure Detection (LCD) is an essential task in robotics and computer vision, serving as a fundamental component for various applications across diverse domains. These applications encompass object recognition, image retrieval, and video analysis. LCD consists in identifying whether a robot has returned to a previously visited location, referred to as a loop, and then estimating the related roto-translation with respect to the analyzed location. Despite the numerous advantages of radar sensors, such as their ability to operate under diverse weather conditions and provide a wider range of view compared to other commonly used sensors (e.g., cameras or LiDARs), integrating radar data remains an arduous task due to intrinsic noise and distortion. To address this challenge, this research introduces RadarLCD, a novel supervised deep learning pipeline specifically designed for Loop Closure Detection using the FMCW Radar (Frequency Modulated Continuous Wave) sensor. RadarLCD, a learning-based LCD methodology explicitly designed for radar systems, makes a significant contribution by leveraging the pre-trained HERO (Hybrid Estimation Radar Odometry) model. Being originally developed for radar odometry, HERO's features are used to select key points crucial for LCD tasks. The methodology undergoes evaluation across a variety of FMCW Radar dataset scenes, and it is compared to state-of-the-art systems such as Scan Context for Place Recognition and ICP for Loop Closure. The results demonstrate that RadarLCD surpasses the alternatives in multiple aspects of Loop Closure Detection.