Abstract
The problem of 2D instantaneous ego-motion estimation for vehicles equipped with automotive radars is studied. To leverage multi-dimensional radar point clouds and exploit point features automatically, without human engineering, a novel approach is proposed that transforms ego-motion estimation into a weighted least squares (wLSQ) problem using neural networks. Comparison with existing methods is done using a challenging real-world radar dataset. The comparison results show that the proposed method can achieve better performance in terms of estimation accuracy, long-term stability, and runtime performance compared to a representative approach selected from the recent literature.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 2023 20th European Radar Conference (EuRAD) |
| Publisher | IEEE |
| Pages | 201-204 |
| Number of pages | 4 |
| ISBN (Electronic) | 978-2-87487-074-3 |
| ISBN (Print) | 979-8-3503-2246-0 |
| DOIs | |
| Publication status | Published - 2023 |
| Event | 2023 20th European Radar Conference (EuRAD) - Berlin, Germany Duration: 20 Sept 2023 → 22 Sept 2023 Conference number: 20th |
Publication series
| Name | 20th European Radar Conference, EuRAD 2023 |
|---|
Conference
| Conference | 2023 20th European Radar Conference (EuRAD) |
|---|---|
| Country/Territory | Germany |
| City | Berlin |
| Period | 20/09/23 → 22/09/23 |
Bibliographical note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-careOtherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Keywords
- Automotive Radar
- Ego-motion Estimation
- Radar Point Cloud
- Deep Learning