Presentation
Error Type Influences Communication Recipient Selection: Consistent Patterns During Autonomy and Automation Errors in a Synthetic Task Environment
DescriptionEffective communication in human-autonomy teams is crucial for optimizing error management during autonomy or automation failures. This study explores how error type (autonomy vs. automation failures) determines how human team members communicate the error and examines whether training interventions (control, trust calibration, or coordination training) influence these behaviors in text-based communication channels. Previously collected data from an experiment conducted in a synthetic task environment designed for team reconnaissance tasks (CERTT-RPAS-STE; Cooke & Shope, 2004) was analyzed using multilevel logistic regression. Results indicated that human team members were less likely to communicate with other human team members during autonomy failures (when the AI teammate malfunctions) compared to automation failures (when the operating system fails, such as display failures), regardless of training type. These findings help to understand the decision-making process of human teammates in managing errors during unexpected automation and autonomy failures.
Event Type
Industry/Practitioner Content
Lecture
TimeWednesday, October 15th3:20pm - 3:40pm CDT
LocationGrand B
Human AI Robot Teaming (AI)