arXiv:2505.22783v2 Announce Type: replace-cross Abstract: Reliable altitude estimation with frequency-modulated continuous wave (FMCW) radar altimeters is increasingly a challenge due to in-band interference from modern communication systems. In this paper, we present a temporal convolutional autoencoder (TCAE) that directly processes in-phase and quadrature (IQ) samples to suppress structured interference while preserving signal phase and frequency content for range estimation. The model is trained and initially evaluated within a full radar altimeter simulation chain, then further validated
The rapid proliferation of modern communication systems is creating significant in-band interference for critical technologies like FMCW radar altimeters, making advanced mitigation techniques urgently necessary for reliable operation.
Reliable radar altimetry is crucial for autonomous systems, aviation safety, and defense applications, highlighting the importance of solutions that maintain functionality amidst increasing electromagnetic spectrum contention.
Traditional interference mitigation methods are becoming insufficient, and this AI-driven approach offers a significant improvement in maintaining signal integrity for critical range estimation in challenging environments.
- · Aerospace and Defense contractors
- · AI/ML research institutions
- · Autonomous vehicle developers
- · Developers reliant on legacy interference mitigation techniques
- · Communication system providers (if their systems are redesigned to be less intru
Improved reliability and safety for aircraft and autonomous systems using FMCW radar altimeters.
Accelerated adoption of AI/ML techniques for signal processing in other critical sensor systems facing similar interference challenges.
Broader integration of AI into defence and aerospace hardware as a standard feature, rather than an add-on.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG