Preliminary Interactions of Human-Robot Trust, Cognitive Load, and Robot Intelligence Levels in a Competitive Game

Abstract

This paper presents a pilot study in which we examine the interactions between human-robot teammate trust, cognitive load, and robot intelligence levels. In particular, we attempt to assess these interactions during a competitive game of capture the flag played between a human and a robot. We present results while the human plays against robots of different intelligence levels and determines their level of trust of each robot as a potential teammate through a post experiment questionnaire. We also present our exploration of heart rate measures as approximations of cognitive load. It is our goal to determine guidelines for future autonomy and interaction designers such that their systems will reduce cognitive load and increase the level of trust in robot teammates. This is an initial experiment that uses the least amount of vehicles yet still gathers competitive data on the water. Future experiments will increase in complexity to many opponents and many teammates.