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.
Recommended Citation
St. Louis, August, "Analyzing the Influence of Stale Data on Autonomous Intelligent Transportation Systems" (2023). All Theses. 3981.
https://tigerprints.clemson.edu/all_theses/3981