Active Sensing with Meta-Reinforcement Learning for Emitter Localization from RF Observations

2026-05-12

AI Summary

This study addresses the challenge of localizing GNSS jammers in complex indoor multipath environments, where signal ambiguity and time-varying channels severely hinder performance. The problem is formulated as a partially observable active sensing task, and this work proposes a novel approach that integrates meta-reinforcement learning with high-dimensional radio-frequency (RF) perception. Leveraging RF sequences captured by a 2×2 patch antenna array, recurrent neural network–enhanced DQN and PPO agents recursively explore the environment to infer jammer locations. Trained on ray-traced channel data generated with the Sionna simulator, the method achieves an 80.1% localization success rate across diverse scenarios, demonstrating significantly improved robustness against multipath effects and domain shifts. These results validate the effectiveness of reinforcement learning for adaptive source localization in complex electromagnetic environments.

Abstract

Global navigation satellite system (GNSS) interference poses a serious threat to reliable positioning, especially in indoor and multipath-rich environments where source localization is highly challenging. In this paper, we formulate GNSS interference localization as an active sensing problem and propose a reinforcement learning (RL) framework in which an agent sequentially explores the environment to infer the position of an emitter source from radio frequency (RF) observations acquired with a 2x2 patch antenna. The localization task is modeled as a partially observable decision process, since single-snapshot measurements are often ambiguous under multipath propagation and changing channel conditions. To address this, the proposed framework combines high-dimensional RF sensing with deep RL and recurrent policy learning. We investigate both value-based and policy-based approaches, namely Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO), and study their behavior under domain shift. The approach is evaluated on a simulated dataset generated with the Sionna ray-tracing module, which provides realistic propagation effects and diverse environment configurations. Experimental results show that the proposed method achieves a localization success rate of 80.1%, demonstrating the potential of RL for adaptive GNSS interference localization. Overall, the results highlight simulation-assisted training as a promising direction for robust interference localization in challenging propagation environments.

Problem

• GNSS interference
• emitter localization
• active sensing
• multipath propagation
• RF observations

Innovation

• active sensing
• meta-reinforcement learning
• emitter localization
• radio frequency (RF) observations
• partially observable MDP