Learning Car Speed Using Inertial Sensors for Dead Reckoning Navigation

TL;DR

This paper presents a deep neural network approach using inertial sensors to estimate car speed for dead reckoning navigation, improving position accuracy in urban environments without relying on GNSS signals.

Contribution

It introduces a novel LSTM-based DNN model trained on urban driving data to accurately estimate vehicle speed from low-cost IMU sensors for dead reckoning.

Findings

Significant reduction in position error during 4-minute drive

Effective high-frequency speed estimation from inertial data

Improved dead reckoning accuracy without GNSS updates

Abstract

A deep neural network (DNN) is trained to estimate the speed of a car driving in an urban area using as input a stream of measurements from a low-cost six-axis inertial measurement unit (IMU). Three hours of data was collected by driving through the city of Ashdod, Israel in a car equipped with a global navigation satellite system (GNSS) real time kinematic (RTK) positioning device and a synchronized IMU. Ground truth labels for the car speed were calculated using the position measurements obtained at the high rate of 50 Hz. A DNN architecture with long short-term memory layers is proposed to enable high-frequency speed estimation that accounts for previous inputs history and the nonlinear relation between speed, acceleration and angular velocity. A simplified aided dead reckoning localization scheme is formulated to assess the trained model which provides the speed pseudo-measurement. The trained model is shown to substantially improve the position accuracy during a 4 minutes drive without the use of GNSS position updates.