Shared Learning Effects in Evaluations of Machine Teammates

In teams of humans and several robots, communication within the robot subgroup may occur without the human being necessarily aware of this, e.g., to update each other about task-relevant aspects of the environment. Nonetheless, since this affects their subsequent actions and visible behaviour, it has consequences for teamwork and the humans' perception of the team, which are not always well-understood. Intra-robot communication and coordination can be beneficial, but may also be experienced negatively due to unexpected group dynamics. In this study, we designed three robot teams, with varying levels of shared learning: one where robots share information about the environment and other robots acknowledge receiving this information, one where this information is shared but receipt is not acknowledged, and one where there is no communication. In each case, robots assisted a human participant in repairing pipes in a simulated environment. We measured perceived entitativity, trust, and attribution of mind to the robots. Overall, our results illustrate that improving the skills of robots (in this case, shared learning) is not sufficient to also improve the human experience of being a member of such a team. How humans perceive artificial agents can be more important than their actual abilities. We thus explore implications for improving the human teammate's understanding of robotic (social) abilities in hybrid teams.