Semi-Supervised Contrastive Learning for Few-Shot Indoor Positioning via 5G NR

Leveraging the enhanced bandwidth and the advantages conferred by Massive Multiple-Input Multiple-Output (MIMO) technology, 5G New Radio (NR) extends unprecedented prospects for high-fidelity indoor positioning systems. However, the expensive equipment required for 5G CSI collection and the complex workforce involved often lead to a scarcity of "CSI-position" samples, hindering the deployment of deep learning (DL)-based fingerprint positioning methods. In this paper, a novel semi-supervised contrastive learning method is proposed for few-shot 5G fingerprint positioning to fully leverage the untapped potential of unlabeled 5G CSI data in modeling the "CSI to position" representation. Specifically, we encourage consistent representations of the same CSI under different channel conditions and propose a straightforward yet effective technique to simulate positive samples from diverse channel conditions. Additionally, we introduce range encoding to facilitate subcarrier strength position awareness for 5G CSI. Experimental results on 1000 location samples in a training-unknown positioning setting demonstrate that our method, with just fine-tuning an MLP, can achieve performance comparable to fully supervised approaches. Our code can be accessed at https://github.com/mxx123321/few-shot-learning-for-5G-indoor-positioning.

I. Introduction

While Global Positioning System (GPS) technology offers considerable accuracy for outdoor localization, it encounters significant constraints in regions fraught with dense structural impediments. Notably, environments like indoor spaces, urban canyons, or subterranean parking facilities pose challenges wherein GPS signals are susceptible to interference or may be rendered entirely inaccessible. In such scenarios, extensive research has been conducted on fingerprint-based indoor high-precision localization [1].