Towards Improved Inertial Navigation by Reducing Errors Using Deep Learning Methodology

Date of Award

2022

Degree Name

Ph.D. in Electrical and Computer Engineering

Department

Department of Electrical and Computer Engineering

Advisor/Chair

Vamsy Chodavarapu

Abstract

Autonomous vehicles make use of an Inertial Navigation System (INS) as part of vehicular sensor fusion in many situations including Global Navigation Satellite System (GNSS)- denied environments such as dense urban places, multi-level parking structures, and areas with thick tree-coverage. The INS unit incorporates an Inertial Measurement Unit (IMU) to process the linear acceleration and angular velocity data to obtain orientation, position and velocity information using mechanization equations. In this work, we developed a novel deep learning-based methodology, using Convolutional Neural Networks (CNN) to reduce errors from MEMS IMU sensors. We developed a methodology of using CNN algorithms that can learn from the responses of a particular inertial sensor while subject to inherent noise errors and provide a near real-time error correction. We implemented a time-division method to divide the IMU output data into small step sizes. By using this method, we make the IMU outputs fit the input format of the CNN. We optimized the CNN algorithm for higher performance and lower complexity that would allow its implementation on ultra-low power hardware such as microcontrollers. We examined the performance of our CNN algorithm under various situations with IMUs of various performance grades, IMUs of the same type but different manufactured batch, and controlled, fixed and un-controlled vehicle motion paths.

Keywords

Electrical Engineering, Inertial navigation, Inertial measurement unit, MEMS IMU, Deep learning, Autonomous driving

Rights Statement

Copyright © 2022, author

Link to Full Text

Share

COinS