Date of Award

5-2023

Document Type

Thesis

Degree Name

Master of Engineering (MEngr)

Department

Computer Engineering

Committee Chair/Advisor

Jon Calhoun

Committee Member

Jerome McClendon

Committee Member

Melissa Smith

Abstract

Intelligent transportation has been at the forefront of recent technological advancement. Individuals have developed a number of algorithms intended to automate and improve essential intelligent transportation functions. New developments include the incorporation of vehicle platooning and path planning algorithms within a number of use cases. Data perturbation can affect both algorithms significantly. We define data perturbation as any natural or unnatural phenomenon that causes the data to be skewed in any way. Perturbations within either system can cause its respective algorithm to operate with stale or incorrect data. This can significantly affect performance. This paper conducts a fault injection campaign to analyze the impact of data perturbations in platooning and path planning models. This campaign enters perturbed data into each model to simulate the several unknown occurrences that may arise. Our analysis provides an understanding of model parameter sensitivity for causing system failures. By understanding which parameters are most influential to the fidelity of the model, we gain the ability to make intelligent transportation algorithms safer.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.