Saved in:
Bibliographic Details
Main Authors: An, Tong, Lu, Huan, Shi, Jiayang, Yu, Kai, Zhu, Rongrong, Zheng, Bin, Zhao, Jiwei, Zhou, Haibo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.00696
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914298381467648
author An, Tong
Lu, Huan
Shi, Jiayang
Yu, Kai
Zhu, Rongrong
Zheng, Bin
Zhao, Jiwei
Zhou, Haibo
author_facet An, Tong
Lu, Huan
Shi, Jiayang
Yu, Kai
Zhu, Rongrong
Zheng, Bin
Zhao, Jiwei
Zhou, Haibo
contents Achieving ubiquitous high-accuracy localization is crucial for next-generation wireless systems, yet remains challenging in multipath-rich urban environments. By exploiting the fine-grained multipath characteristics embedded in channel state information (CSI), more reliable and precise localization can be achieved. To address this, we present CMANet, a multi-BS cooperative positioning architecture that performs feature-level fusion of raw CSI using the proposed Channel Masked Attention (CMA) mechanism. The CMA encoder injects a physically grounded prior--per-BS channel gain--into the attention weights, thus emphasizing reliable links and suppressing spurious multipath. A lightweight LSTM decoder then treats subcarriers as a sequence to accumulate frequency-domain evidence into a final 3D position estimate. In a typical 5G NR-compliant urban simulation, CMANet achieves less than 0.5m median error and 1.0m 90th-percentile error, outperforming state-of-the-art benchmarks. Ablations verify the necessity of CMA and frequency accumulation. CMANet is edge-deployable and exemplifies an Integrated Sensing and Communication (ISAC)-aligned, cooperative paradigm for multi-BS CSI positioning.
format Preprint
id arxiv_https___arxiv_org_abs_2602_00696
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CMANet: Channel-Masked Attention Network for Cooperative Multi-Base-Station 3D Positioning
An, Tong
Lu, Huan
Shi, Jiayang
Yu, Kai
Zhu, Rongrong
Zheng, Bin
Zhao, Jiwei
Zhou, Haibo
Signal Processing
Achieving ubiquitous high-accuracy localization is crucial for next-generation wireless systems, yet remains challenging in multipath-rich urban environments. By exploiting the fine-grained multipath characteristics embedded in channel state information (CSI), more reliable and precise localization can be achieved. To address this, we present CMANet, a multi-BS cooperative positioning architecture that performs feature-level fusion of raw CSI using the proposed Channel Masked Attention (CMA) mechanism. The CMA encoder injects a physically grounded prior--per-BS channel gain--into the attention weights, thus emphasizing reliable links and suppressing spurious multipath. A lightweight LSTM decoder then treats subcarriers as a sequence to accumulate frequency-domain evidence into a final 3D position estimate. In a typical 5G NR-compliant urban simulation, CMANet achieves less than 0.5m median error and 1.0m 90th-percentile error, outperforming state-of-the-art benchmarks. Ablations verify the necessity of CMA and frequency accumulation. CMANet is edge-deployable and exemplifies an Integrated Sensing and Communication (ISAC)-aligned, cooperative paradigm for multi-BS CSI positioning.
title CMANet: Channel-Masked Attention Network for Cooperative Multi-Base-Station 3D Positioning
topic Signal Processing
url https://arxiv.org/abs/2602.00696