Deep Learning Based Speed Estimation for Constraining Strapdown Inertial Navigation on Smartphones

TL;DR

This paper introduces a deep learning approach to improve smartphone inertial navigation by estimating speed from IMU data, enhancing odometry accuracy on low-grade sensors.

Contribution

It presents a novel CNN-based model for real-time speed inference that complements traditional inertial navigation systems on smartphones.

Findings

Model successfully infers speed from IMU data.

Combining the model with inertial navigation improves 3D localization.

Feasibility demonstrated on iPhone data.

Abstract

Strapdown inertial navigation systems are sensitive to the quality of the data provided by the accelerometer and gyroscope. Low-grade IMUs in handheld smart-devices pose a problem for inertial odometry on these devices. We propose a scheme for constraining the inertial odometry problem by complementing non-linear state estimation by a CNN-based deep-learning model for inferring the momentary speed based on a window of IMU samples. We show the feasibility of the model using a wide range of data from an iPhone, and present proof-of-concept results for how the model can be combined with an inertial navigation system for three-dimensional inertial navigation.