Bayesian Jammer Localization with a Hybrid CNN and Path-Loss Mixture of Experts
This work addresses GNSS jamming localization for urban applications, representing an incremental improvement over previous data-driven methods.
The paper tackled the problem of localizing GNSS jammers in urban environments by proposing a hybrid Bayesian mixture-of-experts framework that fuses a physical path-loss model with a CNN, resulting in improved localization accuracy and reduced uncertainty as training points increase.
Global Navigation Satellite System (GNSS) signals are vulnerable to jamming, particularly in urban areas where multipath and shadowing distort received power. Previous data-driven approaches achieved reasonable localization but poorly reconstructed the received signal strength (RSS) field due to limited spatial context. We propose a hybrid Bayesian mixture-of-experts framework that fuses a physical path-loss (PL) model and a convolutional neural network (CNN) through log-linear pooling. The PL expert ensures physical consistency, while the CNN leverages building-height maps to capture urban propagation effects. Bayesian inference with Laplace approximation provides posterior uncertainty over both the jammer position and RSS field. Experiments on urban ray-tracing data show that localization accuracy improves and uncertainty decreases with more training points, while uncertainty concentrates near the jammer and along urban canyons where propagation is most sensitive.