Joint Localization and Orientation with Triple-Beam Fingerprints in Massive MIMO-OFDM

2026-05-26

AI Summary

This work addresses the limitations of conventional fingerprinting-based localization methods, which rely solely on spatial information while ignoring user motion dynamics and the inherent sparsity of channel fingerprints. To overcome these issues, the authors propose a three-beam fingerprint (TBF) that integrates Doppler information and develop LOA-Net, a Transformer-based network for joint user position and orientation estimation in massive MIMO-OFDM systems. The approach innovatively embeds Doppler features into a compact, sparse TBF representation and introduces two key modules: a mask-enhanced MaskDETR-Reg regression module for precise localization and a fusion-enhanced Fusion-TDC classification module for orientation inference, enabling unified modeling across angle, delay, and Doppler domains. Evaluated under the 3GPP 38.901 indoor scenario, the method significantly outperforms WKNN and 2D/3D CNN baselines in localization accuracy while achieving high-fidelity orientation estimation.

Abstract

With the widespread application of location-based services, fingerprint-based localization has demonstrated advantages in environments with complex signal propagation. Deep learning has significantly improved the efficiency of both offline training and online matching in localization processes. However, existing fingerprints only contain terminal position information without capturing motion states, and neural network designs have not fully incorporated structural features such as fingerprint sparsity. In this paper, we propose a triple-beam fingerprint (TBF) incorporating Doppler information and design a Transformer-based localization and orientation awareness network (LOA-Net) to simultaneously estimate user position and motion direction in massive multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) systems. We first show the correlation between TBF and multipath information, and investigate the collinearity of different TBFs, demonstrating that TBF is an effective small-size sparse fingerprint. Then, we propose LOA-Net containing a mask-augmented detection Transformer for regression (MaskDETR-Reg) module and a fusion-enhanced Transformer for direction classification (Fusion-TDC) module to process angle-delay domain information and Doppler domain information, respectively. Finally, in the simulation of indoor scenarios defined in 3GPP 38.901, the proposed method achieves significantly better localization accuracy than weighted $K$-nearest neighbors (WKNN), 2D and 3D convolutional neural networks (CNNs), and achieves satisfactory motion direction estimation accuracy.

Problem

• fingerprint-based localization
• motion direction estimation
• massive MIMO-OFDM
• Doppler information
• sparse fingerprint

Innovation

• Triple-Beam Fingerprint
• Doppler-aware Localization
• Transformer-based Network
• Joint Position and Orientation Estimation
• Massive MIMO-OFDM