Unsupervised Radio Map Construction in Mixed LoS/NLoS Indoor Environments

2025-10-09

AI Summary

To address the high cost of position labeling in indoor radio map construction, this paper proposes an unsupervised trajectory recovery method that jointly infers user mobility trajectories and propagation environment states (LOS/NLOS) directly from MIMO channel state information (CSI) sequences—without any location labels. We innovatively formulate a hidden Markov model (HMM) framework that jointly models CSI power, delay, and angle features, while tightly coupling a Gaussian–Markov trajectory model with an environment classifier. This marks the first unsupervised approach enabling automatic LOS/NLOS identification and integrated modeling in MIMO systems. Evaluated in a simulated MIMO-OFDM environment, our method achieves a localization accuracy of 0.65 m. The resulting radio maps significantly outperform supervised baselines—including KNN, SVM, and DNN—demonstrating substantial gains in both mapping fidelity and generalization. Our approach effectively alleviates the annotation bottleneck in radio map construction.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Semi-Supervised Learning

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Radio maps are essential for enhancing wireless communications and localization. However, existing methods for constructing radio maps typically require costly calibration pro- cesses to collect location-labeled channel state information (CSI) datasets. This paper aims to recover the data collection trajectory directly from the channel propagation sequence, eliminating the need for location calibration. The key idea is to employ a hidden Markov model (HMM)-based framework to conditionally model the channel propagation matrix, while simultaneously modeling the location correlation in the trajectory. The primary challenges involve modeling the complex relationship between channel propagation in multiple-input multiple-output (MIMO) networks and geographical locations, and addressing both line-of-sight (LOS) and non-line-of-sight (NLOS) indoor conditions. In this paper, we propose an HMM-based framework that jointly characterizes the conditional propagation model and the evolution of the user trajectory. Specifically, the channel propagation in MIMO networks is modeled separately in terms of power, delay, and angle, with distinct models for LOS and NLOS conditions. The user trajectory is modeled using a Gaussian-Markov model. The parameters for channel propagation, the mobility model, and LOS/NLOS classification are optimized simultaneously. Experimental validation using simulated MIMO-Orthogonal Frequency-Division Multiplexing (OFDM) networks with a multi-antenna uniform linear arrays (ULA) configuration demonstrates that the proposed method achieves an average localization accuracy of 0.65 meters in an indoor environment, covering both LOS and NLOS regions. Moreover, the constructed radio map enables localization with a reduced error compared to conventional supervised methods, such as k-nearest neighbors (KNN), support vector machine (SVM), and deep neural network (DNN).

Problem

• Eliminating location calibration for radio map construction in indoor environments
• Modeling complex MIMO channel propagation relationships with geographical locations
• Addressing both line-of-sight and non-line-of-sight indoor conditions simultaneously

Innovation

• HMM-based framework jointly models propagation and trajectory
• Separate channel modeling for LOS and NLOS conditions
• Simultaneous optimization of propagation and mobility parameters