Session: DTM-11: Artificial Intelligence and Design 1

Paper Number: 148183

148183 - Coaching Engineering Design Teams With a Collective Intelligence-Based Ai Facilitator 

The use of Artificial Intelligence (AI) to guide team dynamics has the potential to transform collaborative problem-solving processes. Existing approaches to doing so are trained on prior problem-specific data, limiting them to problems similar to those that have already been solved. This research extends AI-based approaches to team real-time team guidance to novel situations by eliminating the need for prior data. This is accomplished by focusing on team communication via the psychological construct of collective intelligence (CI) rather than problem-specific strategies.
CI is the general ability of a team to work well together across various tasks and is more predictive of team performance than individual intelligence. The strongest predictor of collective intelligence is social sensitivity, a person’s capacity to detect and comprehend the emotions and perspectives of others. More specifically, the teammate with the lowest social sensitivity has the largest negative impact on team performance overall [1], [2], [3]. This work introduces an AI facilitator that monitors several CI attributes in real-time and intervenes as necessary to guide human teams towards better collaboration and overall performance.
Specifically, the AI facilitator monitors collective attention, consistent communication, equal participation. Collective attention in a team context means teammates are aligned with the same goals and engaged in concentrated interactions [4], [5]. Consistent communication is related to coordinated attention; it refers to preventing teammates from dropping out of a discussion and becoming disengaged [6]. Equal participation is a team dynamic attribute where ideally each teammate contributes equally to a conversation. Ensuring that each team member’s thoughts are heard promotes a collaborative environment leading to better group performance. 
The AI facilitator is tested in a human subjects study performed on teams working together to design a mechanical system. The study's findings support that the AI facilitator leads teams to solutions of significantly higher quality. This contribution to the field of AI in team management is notable because of the elimination of the need for prior data, making it applicable to novel problem-solving situations. This work lays the groundwork for a new approach to potentially transform the future of teamwork.
 

Presenting Author: Scotty Mcgee Carnegie Mellon University

Presenting Author Biography: Grad student at CMU

Authors:

Scotty Mcgee Carnegie Mellon University
Jonathan Cagan Carnegie Mellon University
Christopher Mccomb Carnegie Mellon University