Rad-R: A Raw-ADC Radar Dataset and Capture-Invariant SSM for Hardware-Fault Diagnosis
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created Rad-R, a dataset of raw radar signals from a specialized car radar that includes controlled hardware problems like vibration and antenna issues. Each recording is paired with precise measurements of the fault and synchronized data from other sensors like cameras and GPS. They tested various AI models to see how well they can handle these faults, finding that some methods work well within the same conditions but struggle when faults vary. Their new model, RadrNet-DS-CI, performs best at handling different severity levels of faults. The dataset and code will be publicly shared to support further research.
mmWave radarraw-ADC dataantenna misalignmentradome blockageIMU (Inertial Measurement Unit)micro-Dopplercross-severity generalisationRadrNetmacro-F1 scorefew-shot learning
Authors
Mainak Mallick, Junghwan Yim, Seung-Kyum Choi
Abstract
Automotive mmWave radar can develop vibration, antenna misalignment, radome blockage, and receive-channel degradation that corrupt the signal before perception begins. Data for these faults are scarce because each condition must be induced and measured on physical hardware. We introduce Rad-R, a raw-ADC dataset captured with a 4-chip 77GHz TI MMWCAS-RF-EVM cascade (192 virtual channels). Unlike existing raw-radar datasets, Rad-R pairs each recording with a controlled hardware fault at a calibrated severity, an independent physical severity measurement, and frame-synchronised IMU, temperature, GPS, and camera streams. Rad-R is a single-session dataset, so our generalisation claims are confined to a controlled cross-severity protocol in which train and test use physically distinct captures. A reproducible benchmark evaluates seven representative vision backbones and the proposed raw-IQ Mamba SSM (RadrNet) under within-clip, chirp-wise anytime, few-shot cross-capture, and controlled cross-severity protocols. Within-clip performance is near-saturated ($>0.98$ macro-F1), whereas cross-severity generalisation remains difficult: the absolute-phase RadrNet-DS falls to $0.49$ macro-F1. RadrNet-DS-CI replaces absolute phase with per-frame-standardised magnitude and relative chirp-to-chirp phase and ranks first on the controlled benchmark ($0.663$ vs. $0.628$ for the strongest RD-CNN; three seeds); the RadrNet family also leads on the anytime and few-shot budgets. A descriptive cross-modal analysis further finds that radar micro-Doppler covaries with independently measured IMU vibration energy (pooled Spearman $ρ=0.41$ across conditions). The complete dataset and code will be released publicly under permissive licences.