A Physics-Informed Digital Twin Framework for Calibrated Sim-to-Real FMCW Radar Occupancy Estimation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914279795458048 |
|---|---|
| author | Trinh, Huy Ratto V, Sebastian Creager, Elliot Shaker, George |
| author_facet | Trinh, Huy Ratto V, Sebastian Creager, Elliot Shaker, George |
| contents | Learning robust radar perception models directly from real measurements is costly due to the need for controlled experiments, repeated calibration, and extensive annotation. This paper proposes a lightweight simulation-to-real (sim2real) framework that enables reliable Frequency Modulated Continuous Wave (FMCW) radar occupancy detection and people counting using only a physics-informed geometric simulator and a small unlabeled real calibration set. We introduce calibrated domain randomization (CDR) to align the global noise-floor statistics of simulated range-Doppler (RD) maps with those observed in real environments while preserving discriminative micro-Doppler structure. Across real-world evaluations, ResNet18 models trained purely on CDR-adjusted simulation achieve 97 percent accuracy for occupancy detection and 72 percent accuracy for people counting, outperforming ray-tracing baseline simulation and conventional random domain randomization baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_17871 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Physics-Informed Digital Twin Framework for Calibrated Sim-to-Real FMCW Radar Occupancy Estimation Trinh, Huy Ratto V, Sebastian Creager, Elliot Shaker, George Signal Processing Learning robust radar perception models directly from real measurements is costly due to the need for controlled experiments, repeated calibration, and extensive annotation. This paper proposes a lightweight simulation-to-real (sim2real) framework that enables reliable Frequency Modulated Continuous Wave (FMCW) radar occupancy detection and people counting using only a physics-informed geometric simulator and a small unlabeled real calibration set. We introduce calibrated domain randomization (CDR) to align the global noise-floor statistics of simulated range-Doppler (RD) maps with those observed in real environments while preserving discriminative micro-Doppler structure. Across real-world evaluations, ResNet18 models trained purely on CDR-adjusted simulation achieve 97 percent accuracy for occupancy detection and 72 percent accuracy for people counting, outperforming ray-tracing baseline simulation and conventional random domain randomization baselines. |
| title | A Physics-Informed Digital Twin Framework for Calibrated Sim-to-Real FMCW Radar Occupancy Estimation |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2601.17871 |