Survey of metrics for human-robot interaction

Abstract

This paper examines 29 papers that have proposed or applied metrics for human-robot interaction. The 42 metrics are categorized as to the object being directly measured: the human (7), the robot (6), or the system (29). Systems metrics are further subdivided into productivity, efficiency, reliability, safety, and coactivity. While 42 seems to be a large set, many metrics do not have a functional, or generalizable, mechanism for measuring that feature. In practice, metrics for system interactions are often inferred through observations of the robot or the human, introducing noise and error in analysis. The metrics do not completely capture the impact of autonomy on HRI as they typically focus on the agents, not the capabilities. As a result the current metrics are not helpful for determining what autonomous capabilities and interactions are appropriate for what tasks.