Effects of Agent Transparency on Operator Trust

Abstract

We conducted a human-in-the-loop robot simulation experiment. The effects of displaying transparency information, in the interface for an autonomous robot, on operator trust were examined. Participants were assigned to one of three transparency conditions and trust was measured prior to observing the autonomous robotic agent's progress and post observation. Results demonstrated that participants who received more transparency information reported higher trust in the autonomous robotic agent. Overall findings indicate that displaying SAT model-based transparency information on a robotic interface is effective for appropriate trust calibration in an autonomous robotic agent.