AirTags for Human Localization, Not Just Objects

TL;DR

The paper tackles the challenge of achieving centimeter-level indoor localization without manual calibration. It introduces UbiLoc, a calibration-free system that repurposes commercially available Apple AirTags and UWB measurements on user devices to localize the user via multilateration, supported by a novel AirTag selection mechanism. The architecture comprises four modules (Outdoor-Indoor Detection, One-shot Localizer, Multishot Localizer, AirTag Selector) to generate robust position estimates, validated in campus and apartment testbeds with median errors of 26 cm and 31.5 cm, respectively. Key findings include that six AirTags offer optimal balance between accuracy and computation, and that the k-nearest AirTag selection yields the best performance among heuristics. The work demonstrates a practical, deployable, calibration-free alternative for cm-level indoor positioning with significant implications for navigation, emergency services, and accessibility.

Abstract

Indoor localization has become increasingly important due to its wide-ranging applications in indoor navigation, emergency services, the Internet of Things (IoT), and accessibility for individuals with special needs. Traditional localization systems often require extensive calibration to achieve high accuracy. We introduce UbiLoc, an innovative, calibration-free indoor localization system that leverages Apple AirTags in a novel way to localize users instead of tracking objects. By utilizing the ubiquitous presence of AirTags and their Ultra-Wideband (UWB) technology, UbiLoc achieves centimeter-level accuracy, surpassing traditional WiFi and Bluetooth Low Energy (BLE) systems. UbiLoc addresses key challenges, including ranging errors caused by multipath and noise, through a novel AirTag selection technique. The system operates without the need for manual calibration, ensuring robustness and self-maintenance. Deployed on various Apple devices and tested in real-world environments, UbiLoc achieved median localization errors as low as 26 cm in a campus building and 31.5 cm in an apartment setting. These results demonstrate that UbiLoc is the first system to offer reliable, cm-level accuracy using widely available technology without requiring calibration, making it a promising solution for next-generation indoor localization systems.

Figures (9)

• Figure 1: An example of our futuristic vision for an indoor positioning system involves using Apple U1-chip products like AirPods, iWatch, HomePod, and AirTags. In this vision, UbiLoc leverages detected AirTags (anchor points) to localize the user within the testbed, providing a seamless and precise indoor positioning solution.
• Figure 2: AirTags LOS & NLOS experiments.
• Figure 3: UbiLoc architecture.
• Figure 4: In the context of 2D multi-lateration, the user's location can be determined by identifying the intersection area among three rings centered around reference points A, B, and C. Each reference point has its own ring, distinguished by varying widths proportional to the standard deviation observed in the ranging measurements.
• Figure 5: Floor plans of our two evaluation testbeds.