4DEgo: ego-velocity estimation from high-resolution radar data

Research output: Contribution to journalArticleScientificpeer-review

9 Downloads (Pure)


Automotive radars allow for perception of the environment in adverse visibility and weather conditions. New high-resolution sensors have demonstrated potential for tasks beyond obstacle detection and velocity adjustment, such as mapping or target tracking. This paper proposes an end-to-end method for ego-velocity estimation based on radar scan registration. Our architecture includes a 3D convolution over all three channels of the heatmap, capturing features associated with motion, and an attention mechanism for selecting significant features for regression. To the best of our knowledge, this is the first work utilizing the full 3D radar heatmap for ego-velocity estimation. We verify the efficacy of our approach using the publicly available ColoRadar dataset and study the effect of architectural choices and distributional shifts on performance.
Original languageEnglish
Article numberfrsip-03-1198205
JournalFrontiers in Signal Processing
Publication statusPublished - 27 Jun 2023
Publication typeA1 Journal article-refereed


  • ego-motion estimation
  • 4D automotive radar
  • autonomous navigation
  • transformers
  • attention

Publication forum classification

  • Publication forum level 0


Dive into the research topics of '4DEgo: ego-velocity estimation from high-resolution radar data'. Together they form a unique fingerprint.

Cite this