Resilience in Human-AI-Robot Teams: Widening the Scope of Measurement
Event Type
Technical Groups
Human AI Robot Teaming (HART)
TimeThursday, October 7th11:24am - 11:42am EDT
LocationGrand Salon VII
DescriptionThis study explores a dynamical systems approach to measuring a team’s continuously evolving state of resilience in Human–AI–Robot Teaming contexts. An experiment was conducted to elicit and explore variation in team resilience, using a remotely-distributed testbed based on Next Generation Combat Vehicle concepts. Groups of 3-participants were recruited to form teams and completed two ground reconnaissance missions set in Minecraft involving movement, communication, and the identification of battlefield objects such as infantry and obstacles. Throughout these missions, teams experienced various perturbations that required resilience. Preliminary results based on two sample teams are presented to demonstrate a potential team resilience measure, comparing dynamical systems measures and performance outcome measures. Traditional measures of team resilience tend to center on events that demand resilience, but research and practice should aim to broaden the scope of team resilience measures to detect fluctuations in team resilience within everyday teamwork.