PosFormer: Generalizable Indoor Positioning via Global--Local Feature Fusion Network

Ultra-wideband (UWB), a short-pulse radio technology with high time resolution, has shown great potential for high-accuracy indoor positioning. However, UWB-based localization still faces significant challenges in multipath-rich nonline-of-sight (NLOS) environments. Traditional geometry-based positioning methods tend to overestimate distances, while existing deep learning approaches often fail to capture the complex spatial and temporal characteristics of UWB signal propagation, leading to limited positioning accuracy. To address these limitations, we propose a Transformer and convolutional neural network (CNN) dual-fusion network inspired by multipath physical information for indoor positioning, termed PosFormer. The Transformer and CNN modules of PosFormer capture the long-distance dependencies and spatial characteristics of channel impulse responses (CIRs), effectively extracting both global and local multiscale features. In addition, we design a nonadjacent anchor-subsets (NAASs) scheme to enrich the diversity of CIRs and introduce a lightweight transfer learning (TL) framework to improve deployment robustness across environments with limited labeled data. Extensive experiments on public industrial datasets demonstrate that PosFormer achieves a mean absolute error (MAE) of 17.64 cm, significantly outperforming classical models such as CNN, long short-term memory (LSTM), and Transformer. In industrial hall environments with numerous metal obstacles, TL enables the pretrained model to achieve a positioning accuracy of 35.92 cm with only 20% of the fingerprint samples, highlighting its practical value for cross-environment deployment.