While outdoor navigation services are widespread, there is no reliable and universal service for indoor positioning. A recent approach to tackle this problem has been recently published on arXiv.org. It employs a number of different sensors of a smartphone. Network sensors and observed landmarks allow estimating an absolute position. Then, motion and position sensors, such as accelerometer, gyroscope, and magnetometer, are used to estimate user displacement (an approach known as Pedestrian Dead Reckoning, PDR).
Image credit: Mohammed Hassan via Pxhere, CC0 Public Domain
A novelty of this paper is applying a deep learning approach to PDR. Convolutional and recurrent networks extract hidden correlations between different sensors, thus allowing them to cope with sensor noise. Moreover, barometer data is used to recognize the floor change. The system outperforms the International Conference on Indoor Positioning and Indoor Navigation challenge winner’s performance by a wide margin.
We address the indoor localization problem, where the goal is to predict user’s trajectory from the data collected by their smartphone, using inertial sensors such as accelerometer, gyroscope and magnetometer, as well as other environment and network sensors such as barometer and WiFi. Our system implements a deep learning based pedestrian dead reckoning (deep PDR) model that provides a high-rate estimation of the relative position of the user. Using Kalman Filter, we correct the PDR’s drift using WiFi that provides a prediction of the user’s absolute position each time a WiFi scan is received. Finally, we adjust Kalman Filter results with a map-free projection method that takes into account the physical constraints of the environment (corridors, doors, etc.) and projects the prediction on the possible walkable paths. We test our pipeline on IPIN’19 Indoor Localization challenge dataset and demonstrate that it improves the winner’s results by 20% using the challenge evaluation protocol.