Indoor Localization using Compact, Telemetry-Agnostic, Transfer-Learning Enabled Decoder-Only Transformer

TL;DR

Locaris introduces a compact, telemetry‑agnostic, decoder‑only transformer approach for indoor localization. By tokenizing raw Wi‑Fi telemetry and fine‑tuning only lightweight adapters (LoRA) on top of a frozen backbone, it achieves calibration‑free, cross‑device and cross‑environment localization with sub‑meter accuracy ($<1\ \mathrm{m}$) across diverse telemetry. The method demonstrates strong cross‑environment transfer with minimal calibration data, resilience to missing APs and telemetry, and favorable latency and memory characteristics, enabling scalable deployment in large‑scale deployments. This work highlights token‑based regression with LLMs as a practical alternative to traditional fingerprinting and model‑based approaches for real‑world indoor positioning.

Abstract

Indoor Wi-Fi positioning remains a challenging problem due to the high sensitivity of radio signals to environmental dynamics, channel propagation characteristics, and hardware heterogeneity. Conventional fingerprinting and model-based approaches typically require labor-intensive calibration and suffer rapid performance degradation when devices, channel or deployment conditions change. In this paper, we introduce Locaris, a decoder-only large language model (LLM) for indoor localization. Locaris treats each access point (AP) measurement as a token, enabling the ingestion of raw Wi-Fi telemetry without pre-processing. By fine-tuning its LLM on different Wi-Fi datasets, Locaris learns a lightweight and generalizable mapping from raw signals directly to device location. Our experimental study comparing Locaris with state-of-the-art methods consistently shows that Locaris matches or surpasses existing techniques for various types of telemetry. Our results demonstrate that compact LLMs can serve as calibration-free regression models for indoor localization, offering scalable and robust cross-environment performance in heterogeneous Wi-Fi deployments. Few-shot adaptation experiments, using only a handful of calibration points per device, further show that Locaris maintains high accuracy when applied to previously unseen devices and deployment scenarios. This yields sub-meter accuracy with just a few hundred samples, robust performance under missing APs and supports any and all available telemetry. Our findings highlight the practical viability of Locaris for indoor positioning in the real-world scenarios, particularly in large-scale deployments where extensive calibration is infeasible.

Figures (12)

• Figure 1: Traditional- & Locaris' GPT.
• Figure 2: Locaris: System Architecture
• Figure 3: Telemetry pipeline
• Figure 4: Locaris vs. baselines in few-shot learning (Lecture target).
• Figure 5: Locaris vs. baselines in few-shot learning (Corridor target).