DoorINet: A Deep-Learning Inertial Framework for Door-Mounted IoT Applications

Abstract

Many Internet of Things applications utilize low-cost, micro, electro-mechanical inertial sensors. A common task is orientation estimation. To tackle such a task, attitude and heading reference system algorithms are applied. Relying on the gyroscope readings, the accelerometer readings are used to update the attitude angles, and magnetometer measurements are utilized to update the heading angle. In indoor environments, magnetometers suffer from interference that degrades their performance. This mainly influences applications focused on estimating the heading angle like finding the heading angle of a closet or fridge door. To circumvent such situations, we propose DoorINet, an end-to-end deep-learning framework to calculate the heading angle from door-mounted, low-cost inertial sensors without using magnetometers. To evaluate our approach, we record a unique dataset containing 391 minutes of accelerometer and gyroscope measurements and corresponding ground-truth heading angle. We show that our proposed approach outperforms commonly used, model based approaches and data-driven methods.