Date of Award
2023
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Computer Science
Committee Chair
Vineetha Menon
Committee Member
Bryan Mesmer
Committee Member
Harry Delugach
Subject(s)
Human-computer interaction, Artificial intelligence, Virtual reality, Pattern recognition systems, Explainable AI (XAI)
Abstract
The exponential nature by which Artificially Intelligent (AI) models grow enables evermore complex tasks to be achieved. Since these tasks tend to augment human capability, interacting with these models presents a unique way to commission assistive automation. The introduction of Explainable AI (XAI) enables AI stakeholders to converse with models, understand model reasonings, and comprehend biases while considering reliability requirements. The introduction of this Explainable capability in Human-AI teams presents a unique approach to addressing the complexities behind Human-Computer Interactions. Our application of Explainable AI for Intelligent Systems to augment decision-making is poised to shine a light on the challenges, feasibility, and considerations for adoption in real-time explainable systems. This thesis presents several contributions including: a virtual environment to measure the Human-AI teaming dynamic, an analysis of the experimental behaviors observed in this team, and the framework we use to integrate AI model explanations into our virtual environment.
Recommended Citation
Schwalb, Joseph, "A study of explainable real-time object detection and human-AI teaming interactions in virtual environments" (2023). Theses. 614.
https://louis.uah.edu/uah-theses/614