Automotive Radar Interference Mitigation with Unfolded Robust PCA based on Residual Overcomplete Auto-Encoder Blocks

TL;DR

This paper introduces a novel deep learning approach combining unfolded robust PCA with residual overcomplete auto-encoder blocks to effectively mitigate automotive radar interference and recover both amplitude and phase of targets.

Contribution

The paper proposes a new unfolded RPCA method with residual overcomplete auto-encoder blocks, significantly improving interference mitigation in automotive radar signals.

Findings

Outperforms existing unfolded RPCA and deep learning models

Accurately estimates both amplitude and phase of targets

Enhances radar detection performance in interference scenarios

Abstract

In autonomous driving, radar systems play an important role in detecting targets such as other vehicles on the road. Radars mounted on different cars can interfere with each other, degrading the detection performance. Deep learning methods for automotive radar interference mitigation can succesfully estimate the amplitude of targets, but fail to recover the phase of the respective targets. In this paper, we propose an efficient and effective technique based on unfolded robust Principal Component Analysis (RPCA) that is able to estimate both amplitude and phase in the presence of interference. Our contribution consists in introducing residual overcomplete auto-encoder (ROC-AE) blocks into the recurrent architecture of unfolded RPCA, which results in a deeper model that significantly outperforms unfolded RPCA as well as other deep learning models.