Date of Award

Spring 2023

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Yahyasoltani, Nasim

Second Advisor

Puri, Satish

Third Advisor

Kaczmarek, Thomas

Abstract

Perhaps the crown jewel of AI is the self-navigating agent. To take many sources of data as input and use it to traverse complex and varied areas while mitigating risk and damage to the vehicle that is being controlled, visual object detection is a key part of the overall suite of this technology. While much efforts are being put towards real-world applications, for example self-driving cars, healthcare related issues and automated manufacturing, we apply object detection in a different way; the automation of movement across a video game play field. We take the TensorFlow Object Detection API and use it to craft an avoidance system in conjunction with a Java front end that allows fire and forget movement to augment normal play.

COinS