Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Bluetooth Low Energy Dataset Using In-Phase and Quadrature Samples for Indoor Localization

Samuel G. Leitch, Qasim Zeeshan Ahmed, Ben Van Herbruggen, Mathias Baert, Jaron Fontaine, Eli De Poorter, Adnan Shahid, Pavlos I. Lazaridis

TL;DR

This work develops a BLE indoor localization framework by collecting raw IQ samples with TI BOOSTXL-AOA hardware and automating ground-truth labeling via a MoCap system. It provides a rich dataset across multiple tag heights and distances while incorporating obstacle scenarios, enabling robust learning for AoA and distance estimation. Validation against the TI PDoA baseline shows competitive angle estimates, with region-specific MAE around $15.42^\circ$ in $[-50^\circ,50^\circ]$, and a Gaussian Process Regression model achieving distance MAE of $0.174$m. The dataset thus offers a practical, reusable resource for advancing BLE-based indoor localization and establishing baselines for AoA and range estimation methods in realistic environments.

Abstract

One significant challenge in research is to collect a large amount of data and learn the underlying relationship between the input and the output variables. This paper outlines the process of collecting and validating a dataset designed to determine the angle of arrival (AoA) using Bluetooth low energy (BLE) technology. The data, collected in a laboratory setting, is intended to approximate real-world industrial scenarios. This paper discusses the data collection process, the structure of the dataset, and the methodology adopted for automating sample labeling for supervised learning. The collected samples and the process of generating ground truth (GT) labels were validated using the Texas Instruments (TI) phase difference of arrival (PDoA) implementation on the data, yielding a mean absolute error (MAE) at one of the heights without obstacles of $25.71^\circ$. The distance estimation on BLE was implemented using a Gaussian Process Regression algorithm, yielding an MAE of $0.174$m.

Bluetooth Low Energy Dataset Using In-Phase and Quadrature Samples for Indoor Localization

TL;DR

This work develops a BLE indoor localization framework by collecting raw IQ samples with TI BOOSTXL-AOA hardware and automating ground-truth labeling via a MoCap system. It provides a rich dataset across multiple tag heights and distances while incorporating obstacle scenarios, enabling robust learning for AoA and distance estimation. Validation against the TI PDoA baseline shows competitive angle estimates, with region-specific MAE around in , and a Gaussian Process Regression model achieving distance MAE of m. The dataset thus offers a practical, reusable resource for advancing BLE-based indoor localization and establishing baselines for AoA and range estimation methods in realistic environments.

Abstract

One significant challenge in research is to collect a large amount of data and learn the underlying relationship between the input and the output variables. This paper outlines the process of collecting and validating a dataset designed to determine the angle of arrival (AoA) using Bluetooth low energy (BLE) technology. The data, collected in a laboratory setting, is intended to approximate real-world industrial scenarios. This paper discusses the data collection process, the structure of the dataset, and the methodology adopted for automating sample labeling for supervised learning. The collected samples and the process of generating ground truth (GT) labels were validated using the Texas Instruments (TI) phase difference of arrival (PDoA) implementation on the data, yielding a mean absolute error (MAE) at one of the heights without obstacles of . The distance estimation on BLE was implemented using a Gaussian Process Regression algorithm, yielding an MAE of m.

Paper Structure

This paper contains 21 sections, 9 equations, 13 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. Contributions
  4. Angle of Arrival (AoA)
  5. Angle of Arrival (AoA) on Bluetooth Low Energy (BLE)
  6. TI PDoA Algorithm
  7. Hardware
  8. Data Collection Strategy
  9. Measurement Environment
  10. Motivation & Measurement Protocol
  11. Measurement Obstacles
  12. Dataset Structure
  13. Recorded Signal Data
  14. Ground Truth (GT) Measurements
  15. Data Validation
  16. ...and 6 more sections

Figures (13)

  • Figure 1: Example of an in-phase and quadrature (IQ) sample stream.
  • Figure 2: Layout of the experimental area. Experiments took place in a 6m x 11m area within a much larger room. Recreated from IIoTLab
  • Figure 3: Analysis of the path traveled by the robot and the consequent GT angles for the three different experiment types. (a) Continuous
  • Figure 4: Analysis of the path traveled by the robot and the consequent GT angles for the three different experiment types. (b) Stopping.
  • Figure 5: Analysis of the path traveled by the robot and the consequent GT angles for the three different experiment types. (c) Continuous zigzag.
  • ...and 8 more figures