Human-Autonomy Teaming and Agent Transparency

Abstract

We developed the user interfaces for two HRI tasking environments based on the Situation awareness-based Agent Transparency (SAT) model: dismounted infantry interacting with a ground robot (Autonomous Squad Member) and human interacting with an intelligent agent to manage a team of heterogeneous robotic vehicles (IMPACT). User testing showed that as agent transparency increased, so did human operator performance and trust calibration effectiveness. The expanded SAT model, which includes Teamwork Transparency, is also briefly described.