Zoom Link: https://cmu.zoom.us/j/99544484313

Title

DeepBLE – Generalizing RSSI based Localization Across Different Devices

Abstract

Accurate smartphone localization ( < 1-meter error) for indoor navigation using only RSSI received from a set of BLE beacons remains a challenging problem, due to the inherent noise of RSSI measurements. To overcome the large variance in RSSI measurements, we propose the use of a deep recurrent neural network, DeepBLE, to localize the smartphone using RSSI measured from multiple beacons in an environment. In particular, we focus on the ability of our approach to generalize across many smartphone brands (e.g., Apple, Samsung) and models (e.g., iPhone 8, S10). Towards this end, we collect a large-scale dataset of 15 hours of smartphone data, which consists of over 50,000 BLE beacon RSSI measurements collected from 47 beacons in a single building using 15 different popular smartphone models, along with precise 2D location annotations. Our experiments show that there is a very high variability of RSSI measurements across smartphone models (especially across brand), making it very difficult to generalize with simple supervised learning using only a subset smartphone models. To address this challenge, we propose a novel statistic similarity loss (SSL) which enables our model to generalize to unseen phones. For known phones, we achieve errors close to 0.8 m, whereas for unseen phones we see cutting error improvement of about 40% from 2.6 m to 1.6 m using our adaptation method.

Committee:

Kris Kitani (Advisor) Michael Kaess Navyata Sanghvi