Transforming Decoder-Only Transformers for Accurate WiFi-Telemetry Based Indoor Localization

2025-05-16

AI Summary

WiFi-based indoor localization suffers from environmental dynamics, multipath effects, and cross-vendor device heterogeneity—e.g., inconsistencies in RSSI, FTM, and CSI formats and feature representations—rendering existing methods, which rely on handcrafted features and scene-specific calibration, poorly generalizable. To address this, we propose WiFiGPT: the first unified wireless localization framework built upon a decoder-only large language model (LLM) architecture inspired by GPT. Crucially, WiFiGPT is the first to employ an LLM as a physical-layer signal regressor, leveraging temporal signal embedding and alignment-normalized modeling of heterogeneous telemetry data (RSSI, FTM, CSI) to enable end-to-end, feature-engineering-free, and calibration-free localization. Experiments demonstrate sub-meter accuracy on RSSI/FTM and centimeter-level accuracy on CSI—consistently outperforming state-of-the-art approaches—and validate the LLM’s strong generalization capability and cross-modal modeling efficacy for wireless sensing tasks.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Wireless Fidelity (WiFi) based indoor positioning is a widely researched area for determining the position of devices within a wireless network. Accurate indoor location has numerous applications, such as asset tracking and indoor navigation. Despite advances in WiFi localization techniques -- in particular approaches that leverage WiFi telemetry -- their adoption in practice remains limited due to several factors including environmental changes that cause signal fading, multipath effects, interference, which, in turn, impact positioning accuracy. In addition, telemetry data differs depending on the WiFi device vendor, offering distinct features and formats; use case requirements can also vary widely. Currently, there is no unified model to handle all these variations effectively. In this paper, we present WiFiGPT, a Generative Pretrained Transformer (GPT) based system that is able to handle these variations while achieving high localization accuracy. Our experiments with WiFiGPT demonstrate that GPTs, in particular Large Language Models (LLMs), can effectively capture subtle spatial patterns in noisy wireless telemetry, making them reliable regressors. Compared to existing state-of-the-art methods, our method matches and often surpasses conventional approaches for multiple types of telemetry. Achieving sub-meter accuracy for RSSI and FTM and centimeter-level precision for CSI demonstrates the potential of LLM-based localisation to outperform specialized techniques, all without handcrafted signal processing or calibration.

Problem

• Improving WiFi-based indoor localization accuracy despite environmental interference
• Addressing vendor-specific WiFi telemetry data variations and formats
• Developing a unified LLM-based model for diverse localization use cases

Innovation

• GPT-based system for WiFi localization
• Handles vendor-specific telemetry variations
• Achieves sub-meter to centimeter-level accuracy