Towards generalized performance metrics for human-robot interaction

Abstract

In order for cognitive robots to act adequately and safely in real world, they must be able to perceive and have abilities of reasoning up to a certain level. Toward this end, performance evaluation metrics are used as important measures to achieve these goals. This paper intends to be a further step towards identifying common metrics for task-oriented human-robot interaction. We believe that within the context of human-robot interaction systems, both human and robot independent actions and joint interactions can significantly affect the quality of the accomplished task, thus proposing a generic performance metric to assess the performance of the human-robot team. Toward the efficient modelling of such metric, we also propose a fuzzy temporal model to evaluate the human trust in automation while interacting with robots and machines to complete some tasks. Trust modelling is critical as it directly influences the interaction time that should be directly and indirectly dedicated toward interacting with the robot. Another fuzzy temporal-based model is also presented to evaluate the human reliability during interaction time, as many research studies state that a large percentage of system failures are due almost equally to humans and machines, and therefore, assessing this important factor in human-robot interaction systems is also crucial. The proposed framework is based on the most recent work in the area of cognitive human-machine interaction and performance evaluation.