Bayesian Jammer Localization with a Hybrid CNN and Path-Loss Mixture of Experts

TL;DR

This paper introduces a hybrid Bayesian model combining physical and neural network components to improve jammer localization in urban GNSS environments, providing accurate position estimates with quantified uncertainty.

Contribution

It presents a novel hybrid Bayesian mixture-of-experts framework that integrates a physical path-loss model with a CNN for urban propagation, enhancing localization accuracy and uncertainty quantification.

Findings

Localization accuracy improves with more training data.

Uncertainty concentrates near the jammer and urban canyons.

The model effectively captures urban propagation effects.

Abstract

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.