CMANet: Channel-Masked Attention Network for Cooperative Multi-Base-Station 3D Positioning

TL;DR

CMANet is a novel multi-base-station 3D positioning method that leverages channel state information with a channel masked attention mechanism, achieving sub-meter accuracy in urban environments.

Contribution

Introduces CMANet, a cooperative multi-BS localization architecture with a physically grounded attention mechanism and frequency accumulation, improving accuracy over existing methods.

Findings

Median error less than 0.5 meters in urban simulations

Outperforms state-of-the-art benchmarks

CMA and frequency accumulation are essential components

Abstract

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.