# UnLoc: A Universal Localization Method for Autonomous Vehicles using LiDAR, Radar and/or Camera Input

arXiv: https://arxiv.org/abs/2307.00741 · HTML: https://mlsanity.com/paper/2307.00741/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 3 Jul 2023.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [Geometry-Aware Learning of Maps for Camera Localization](https://mlsanity.com/paper/1712.03342/) (2017)
- [Image-based localization using LSTMs for structured feature correlation](https://mlsanity.com/paper/1611.07890/) (2016)
- [Modelling Uncertainty in Deep Learning for Camera Relocalization](https://mlsanity.com/paper/1509.05909/) (2015)
- [The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset](https://mlsanity.com/paper/1909.01300/) (2019)
- [AtLoc: Attention Guided Camera Localization](https://mlsanity.com/paper/1909.03557/) (2019)
- [Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network](https://mlsanity.com/paper/1707.09733/) (2017)
- [PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization](https://mlsanity.com/paper/2003.02392/) (2020)
- [Robust and Precise Vehicle Localization based on Multi-sensor Fusion in Diverse City Scenes](https://mlsanity.com/paper/1711.05805/) (2017)
- [SegMap: 3D Segment Mapping using Data-Driven Descriptors](https://mlsanity.com/paper/1804.09557/) (2018)
- [Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar](https://mlsanity.com/paper/2001.10789/) (2020)
- [Masking by Moving: Learning Distraction-Free Radar Odometry from Pose Information](https://mlsanity.com/paper/1909.03752/) (2019)
- [Self-supervised Learning of LiDAR Odometry for Robotic Applications](https://mlsanity.com/paper/2011.05418/) (2020)
- [RadarSLAM: Radar based Large-Scale SLAM in All Weathers](https://mlsanity.com/paper/2005.02198/) (2020)
- [RadarLoc: Learning to Relocalize in FMCW Radar](https://mlsanity.com/paper/2103.11562/) (2021)
- [Sensor Aware Lidar Odometry](https://mlsanity.com/paper/1907.09167/) (2019)
- [Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps](https://mlsanity.com/paper/2301.08957/) (2023)

## Built on by (most cited first, 1 of 1)

- [Automated Road Extraction and Centreline Fitting in LiDAR Point Clouds](https://mlsanity.com/paper/2502.07486/) (2025)

## Abstract (arXiv)

Localization is a fundamental task in robotics for autonomous navigation. Existing localization methods rely on a single input data modality or train several computational models to process different modalities. This leads to stringent computational requirements and sub-optimal results that fail to capitalize on the complementary information in other data streams. This paper proposes UnLoc, a novel unified neural modeling approach for localization with multi-sensor input in all weather conditions. Our multi-stream network can handle LiDAR, Camera and RADAR inputs for localization on demand, i.e., it can work with one or more input sensors, making it robust to sensor failure. UnLoc uses 3D sparse convolutions and cylindrical partitioning of the space to process LiDAR frames and implements ResNet blocks with a slot attention-based feature filtering module for the Radar and image modalities. We introduce a unique learnable modality encoding scheme to distinguish between the input sensor data. Our method is extensively evaluated on Oxford Radar RobotCar, ApolloSouthBay and Perth-WA datasets. The results ascertain the efficacy of our technique.