Near-Field Positioning for XL-MIMO Uniform Circular Arrays: An Attention-Enhanced Deep Learning Approach

TL;DR

This work tackles near-field positioning for XL-MIMO UCAs by introducing an attention-enhanced deep learning model that jointly leverages channel and spatial information. The architecture features a dual-path channel attention module, a deep feature extraction block, a spatial attention block, and an MLP-based regression head, trained on covariance-input data to estimate UE position in polar coordinates $(r,\eta)$, exploiting angle–range coupling in the near-field. Empirical results show the model outperforms ABPN, NFLnet, CNN, and MLP baselines, with covariance-based inputs delivering a substantial accuracy and efficiency edge over CSI. The approach enables sub-meter positioning accuracy with real-time inference, highlighting practical applicability for 6G positioning and IoT scenarios using XL-MIMO UCAs.

Abstract

In the evolving landscape of sixth-generation (6G) mobile communication, multiple-input multiple-output (MIMO) systems are incorporating an unprecedented number of antenna elements, advancing towards Extremely large-scale multiple-input-multiple-output (XL-MIMO) systems. This enhancement significantly increases the spatial degrees of freedom, offering substantial benefits for wireless positioning. However, the expansion of the near-field range in XL-MIMO challenges the traditional far-field assumptions used in previous MIMO models. Among various configurations, uniform circular arrays (UCAs) demonstrate superior performance by maintaining constant angular resolution, unlike linear planar arrays. Addressing how to leverage the expanded aperture and harness the near-field effects in XL-MIMO systems remains an area requiring further investigation. In this paper, we introduce an attention-enhanced deep learning approach for precise positioning. We employ a dual-path channel attention mechanism and a spatial attention mechanism to effectively integrate channel-level and spatial-level features. Our comprehensive simulations show that this model surpasses existing benchmarks such as attention-based positioning networks (ABPN), near-field positioning networks (NFLnet), convolutional neural networks (CNN), and multilayer perceptrons (MLP). The proposed model achieves superior positioning accuracy by utilizing covariance metrics of the input signal. Also, simulation results reveal that covariance metric is advantageous for positioning over channel state information (CSI) in terms of positioning accuracy and model efficiency.

Figures (6)

• Figure 1: Geometric relationship between UCA and UE in near-field region.
• Figure 2: Geometric relationship between ULA and UE in near-field region.
• Figure 3: Architecture of the proposed model
• Figure 4: The CDF of the positioning error of the proposed model, ABPN zhang2024deep, CNN, MLP and NFLnet zhao2024nflnet with various types of input and at different SNR levels.
• Figure 5: Comparison between the proposed model, ABPN zhang2024deep, CNN, MLP and NFLnet zhao2024nflnet in terms of mean and median positioning error at 0 and 20 dB.