Temporal Convolutional Autoencoder for Interference Mitigation in FMCW Radar Altimeters

TL;DR

This paper presents a novel temporal convolutional autoencoder that effectively suppresses interference in FMCW radar altimeters, outperforming traditional methods and operating directly on received signals, with future work aimed at real-time application and robustness.

Contribution

The paper introduces a TCN autoencoder for interference mitigation in FMCW radar altimeters, demonstrating improved performance over LMS filters and highlighting challenges for real-time deployment.

Findings

TCN autoencoder outperforms LMS filter in interference suppression

Method operates directly on FMCW signals, enhancing practicality

Identifies challenges for real-time implementation and generalization

Abstract

We investigate the end-to-end altitude estimation performance of a convolutional autoencoder-based interference mitigation approach for frequency-modulated continuous-wave (FMCW) radar altimeters. Specifically, we show that a Temporal Convolutional Network (TCN) autoencoder effectively exploits temporal correlations in the received signal, providing superior interference suppression compared to a Least Mean Squares (LMS) adaptive filter. Unlike existing approaches, the present method operates directly on the received FMCW signal. Additionally, we identify key challenges in applying deep learning to wideband FMCW interference mitigation and outline directions for future research to enhance real-time feasibility and generalization to arbitrary interference conditions.