Name: Shiwen Zhou

Master’s Thesis Proposal Meeting
Date: November 17, 2021
Time: 4:00 pm
Location: https://bluejeans.com/946703447/3367
 
Advisor:
Jamie Gorman, Ph.D. (Georgia Tech)
 
Thesis Committee Members:

Jamie Gorman, Ph.D. (Georgia Tech)
Richard Catrambone, Ph.D. (Georgia Tech)

James Roberts, Ph.D. (Georgia Tech)

Nancy Cooke, Ph.D. (Arizona State)
 
Title: Communication Pattern Analysis in Human-Autonomy Teaming

Abstract:

Communication is critical to team coordination and interaction because it provides information flow allowing the team to build team cognition, which contributes to overall team performance. In recent years, autonomous artificially intelligent (AI) team members are beginning to be considered as effective substitutes for human teammates. However, research has shown that AI team members lack the communication skills required for effective team performance (McNeese et al., 2018). In this study, I will identify aspects of communication an AI team member does differently compared to a human team member and whether these communication aspects influence team performance. I will analyze the communication features of three-member teams that include all human teams and human-AI teams operating a remotely piloted aircraft system (RPAS). I propose that communication flow and content are the communication features that distinguish communication in all-human teams from communication in human-AI teams. To measure communication flow, I will analyze communication pattern predictability (communication determinism) and communication transition probabilities. To measure communication content, I will use Latent Semantic Analysis (LSA). I propose that these communication flow and content features will predict team performance in all-human versus human-AI teams. In this way, I hope these findings can provide feedback and suggestions to future adoption of AI as a teammate in team training and team operations.