# Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning

arXiv: https://arxiv.org/abs/2105.14152 · HTML: https://mlsanity.com/paper/2105.14152/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2021.

## Built on by (most cited first, 10 of 10)

- [Robust Incremental Structure-from-Motion with Hybrid Features](https://mlsanity.com/paper/2409.19811/) (2024)
- [Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares](https://mlsanity.com/paper/2305.09527/) (2023)
- [Radar Occupancy Prediction with Lidar Supervision while Preserving Long-Range Sensing and Penetrating Capabilities](https://mlsanity.com/paper/2112.04282/) (2021)
- [Improving Extrinsics between RADAR and LIDAR using Learning](https://mlsanity.com/paper/2305.10594/) (2023)
- [Pointing the Way: Refining Radar-Lidar Localization Using Learned ICP Weights](https://mlsanity.com/paper/2309.08731/) (2023)
- [From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers](https://mlsanity.com/paper/2406.07785/) (2024)
- [RaNDT SLAM: Radar SLAM Based on Intensity-Augmented Normal Distributions Transform](https://mlsanity.com/paper/2408.11576/) (2024)
- [RaSCL: Radar to Satellite Crossview Localization](https://mlsanity.com/paper/2504.15899/) (2025)
- [RadarLCD: Learnable Radar-based Loop Closure Detection Pipeline](https://mlsanity.com/paper/2309.07094/) (2023)
- [Towards Multi-Object-Tracking with Radar on a Fast Moving Vehicle: On the Potential of Processing Radar in the Frequency Domain](https://mlsanity.com/paper/2604.14013/) (2026)

## Abstract (arXiv)

This paper presents a radar odometry method that combines probabilistic trajectory estimation and deep learned features without needing groundtruth pose information. The feature network is trained unsupervised, using only the on-board radar data. With its theoretical foundation based on a data likelihood objective, our method leverages a deep network for processing rich radar data, and a non-differentiable classic estimator for probabilistic inference. We provide extensive experimental results on both the publicly available Oxford Radar RobotCar Dataset and an additional 100 km of driving collected in an urban setting. Our sliding-window implementation of radar odometry outperforms most hand-crafted methods and approaches the current state of the art without requiring a groundtruth trajectory for training. We also demonstrate the effectiveness of radar odometry under adverse weather conditions. Code for this project can be found at: https://github.com/utiasASRL/hero_radar_odometry