Dissertation/Thesis Abstract

Locating an Autonomous Car Using the Kalman Filter to Reduce Noise
by Hema Balaji, Nagarathna, M.S., California State University, Long Beach, 2018, 62; 10978429
Abstract (Summary)

With growing use of autonomous vehicles and similar systems, it is critical for those systems to be reliable, accurate, and error free. Sensor data are of vital importance for ensuring the fidelity of navigation and decision-making ability of autonomous systems. Several existing models have achieved accuracy in the sensor data, but they are all application specific and have limited applicability for future systems.

This paper proposes a method for reducing errors in sensor data through use of sensor fusion on the Kalman filter. The proposed model is intended to be versatile and to adapt to the needs of any robotic vehicle with only minor modifications. The model is a basic framework for normalizing the speed of autonomous robots. Moreover, it is capable of ensuring smooth operation of individual autonomous robots and facilitates co-operative applications. The model achieves a framework that is more reliable, accurate, and error free, compared to other existing models, thereby enabling its implementation on similar robotic applications. This model can be expanded for use in other applications with only minimal changes; it therefore promises to revolutionize the way that human beings use, interact with, and benefit from autonomous devices in day-to-day activities.

Indexing (document details)
Advisor: Ponce, Oscar Morales
Commitee: Chelian, Michael, He, Min
School: California State University, Long Beach
Department: Computer Engineering and Computer Science
School Location: United States -- California
Source: MAI 58/04M(E), Masters Abstracts International
Subjects: Computer Engineering, Computer science
Publication Number: 10978429
ISBN: 9780438893528
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy