On the Physical Plausibility and Distribution Alignment for Sim-to-Real RF Positioning
For researchers and engineers working on RF positioning, this work provides practical guidance on sim-to-real transfer, showing that distribution alignment outweighs physical accuracy or data scale.
This paper investigates sim-to-real transfer for RF positioning, finding that aligning the RSSI distribution between simulated and real data is more critical than physical realism or dataset size. The best performance on unseen streets was achieved after normalizing simulated RSSI values to match the real distribution.
Reliable radio frequency (RF) positioning from cellular measurements is limited by the high cost and limited coverage of real drive-test data, especially when models must work on streets not seen during training. Previous work showed that ray tracing simulations can provide useful synthetic data for pretraining deep positioning models. In this paper, we focus on the simulation side and study how base-station calibration, physical realism, synthetic-data scale, and RSSI distribution alignment affect transfer to real data. Using a Sionna reconstruction of a Rome deployment, we calibrate each base station by adjusting its location, height, azimuth, and transmit power. We compare physically plausible calibrations with unconstrained ones that allow unrealistic base-station placements. We also compare deployment-specific synthetic data with much larger city-scale datasets. Although unconstrained calibration matches measured RSSI better, it does not always improve positioning accuracy. All synthetic pretraining approaches improve performance on known streets, with the best result obtained using city-scale unconstrained data. However, larger synthetic datasets alone do not improve performance on unseen streets. The best results on held-out streets are achieved only after normalizing simulated RSSI values to better match the real distribution. Overall, the results suggest that distribution alignment is more important than physical realism or dataset size for sim-to-real RF positioning.