Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

User Localization via Active Sensing with Electromagnetically Reconfigurable Antennas

Ruizhi Zhang, Yuchen Zhang, Ying Zhang

TL;DR

This work tackles accurate user localization in wideband multipath environments by introducing electromagnetically reconfigurable antennas (ERAs) for active sensing. It develops an end-to-end learning framework that jointly optimizes stage-wise sensing configurations and localization through a two-timescale protocol, leveraging attention-based embeddings and an LSTM to progressively refine the UE position with sequential observations, while RA patterns are reconfigured per substage via spherical-harmonic expansions. The approach demonstrates superior localization accuracy over digital beamforming-only and single-stage baselines under varying SNR and pilot budgets, validating the informativeness of ERA-enabled sensing. The framework offers practical impact for future wireless systems by enabling more robust and efficient localization and paves the way for extensions to multi-user and mobile tracking scenarios.

Abstract

This paper presents an end-to-end deep learning framework for electromagnetically reconfigurable antenna (ERA)-aided user localization with active sensing, where ERAs provide additional electromagnetic reconfigurability to diversify the received measurements and enhance localization informativeness. To balance sensing flexibility and overhead, we adopt a two-timescale design: the digital combiner is updated at each stage, while the ERA patterns are reconfigured at each substage via a spherical-harmonic representation. The proposed mechanism integrates attention-based feature extraction and LSTM-based temporal learning, enabling the system to learn an optimized sensing strategy and progressively refine the UE position estimate from sequential observations. Simulation results show that the proposed approach consistently outperforms conventional digital beamforming-only and single-stage sensing baselines in terms of localization accuracy. These results highlight the effectiveness of ERA-enabled active sensing for user localization in future wireless systems.

User Localization via Active Sensing with Electromagnetically Reconfigurable Antennas

TL;DR

This work tackles accurate user localization in wideband multipath environments by introducing electromagnetically reconfigurable antennas (ERAs) for active sensing. It develops an end-to-end learning framework that jointly optimizes stage-wise sensing configurations and localization through a two-timescale protocol, leveraging attention-based embeddings and an LSTM to progressively refine the UE position with sequential observations, while RA patterns are reconfigured per substage via spherical-harmonic expansions. The approach demonstrates superior localization accuracy over digital beamforming-only and single-stage baselines under varying SNR and pilot budgets, validating the informativeness of ERA-enabled sensing. The framework offers practical impact for future wireless systems by enabling more robust and efficient localization and paves the way for extensions to multi-user and mobile tracking scenarios.

Abstract

This paper presents an end-to-end deep learning framework for electromagnetically reconfigurable antenna (ERA)-aided user localization with active sensing, where ERAs provide additional electromagnetic reconfigurability to diversify the received measurements and enhance localization informativeness. To balance sensing flexibility and overhead, we adopt a two-timescale design: the digital combiner is updated at each stage, while the ERA patterns are reconfigured at each substage via a spherical-harmonic representation. The proposed mechanism integrates attention-based feature extraction and LSTM-based temporal learning, enabling the system to learn an optimized sensing strategy and progressively refine the UE position estimate from sequential observations. Simulation results show that the proposed approach consistently outperforms conventional digital beamforming-only and single-stage sensing baselines in terms of localization accuracy. These results highlight the effectiveness of ERA-enabled active sensing for user localization in future wireless systems.
Paper Structure (7 sections, 13 equations, 4 figures)

This paper contains 7 sections, 13 equations, 4 figures.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. System Model
  4. Problem Formulation
  5. Proposed Mechanism
  6. Experiment and Results
  7. Conclusion

Figures (4)

  • Figure 1: The PRA-aided uplink active sensing system.
  • Figure 2: Localization performance comparison: (a) localization RMSE versus stage variation. (b) localization RMSE versus SNR.
  • Figure 3: Localization RMSE versus stage and pilot allocation under fixed total pilots.
  • Figure 4: Stage-wise synthesized beampatterns under $3$ stages with $6$ pilots per stage: (a) Proposed ERA-assisted active sensing. (b) Digital beamformer only.