Uncertainty-Driven Radar-Inertial Fusion for Instantaneous 3D Ego-Velocity Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916796764782592 |
|---|---|
| author | Rai, Prashant Kumar Kowsari, Elham Strokina, Nataliya Ghabcheloo, Reza |
| author_facet | Rai, Prashant Kumar Kowsari, Elham Strokina, Nataliya Ghabcheloo, Reza |
| contents | We present a method for estimating ego-velocity in autonomous navigation by integrating high-resolution imaging radar with an inertial measurement unit. The proposed approach addresses the limitations of traditional radar-based ego-motion estimation techniques by employing a neural network to process complex-valued raw radar data and estimate instantaneous linear ego-velocity along with its associated uncertainty. This uncertainty-aware velocity estimate is then integrated with inertial measurement unit data using an Extended Kalman Filter. The filter leverages the network-predicted uncertainty to refine the inertial sensor's noise and bias parameters, improving the overall robustness and accuracy of the ego-motion estimation. We evaluated the proposed method on the publicly available ColoRadar dataset. Our approach achieves significantly lower error compared to the closest publicly available method and also outperforms both instantaneous and scan matching-based techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_14294 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uncertainty-Driven Radar-Inertial Fusion for Instantaneous 3D Ego-Velocity Estimation Rai, Prashant Kumar Kowsari, Elham Strokina, Nataliya Ghabcheloo, Reza Robotics Artificial Intelligence Signal Processing We present a method for estimating ego-velocity in autonomous navigation by integrating high-resolution imaging radar with an inertial measurement unit. The proposed approach addresses the limitations of traditional radar-based ego-motion estimation techniques by employing a neural network to process complex-valued raw radar data and estimate instantaneous linear ego-velocity along with its associated uncertainty. This uncertainty-aware velocity estimate is then integrated with inertial measurement unit data using an Extended Kalman Filter. The filter leverages the network-predicted uncertainty to refine the inertial sensor's noise and bias parameters, improving the overall robustness and accuracy of the ego-motion estimation. We evaluated the proposed method on the publicly available ColoRadar dataset. Our approach achieves significantly lower error compared to the closest publicly available method and also outperforms both instantaneous and scan matching-based techniques. |
| title | Uncertainty-Driven Radar-Inertial Fusion for Instantaneous 3D Ego-Velocity Estimation |
| topic | Robotics Artificial Intelligence Signal Processing |
| url | https://arxiv.org/abs/2506.14294 |