Robot deception: Recognizing when a robot should deceive

Abstract

This article explores the possibility of developing robot control software capable of discerning when and if a robot should deceive. Exploration of this problem is critical for developing robots with deception capabilities and may lend valuable insight into the phenomena of deception itself. In this paper we explore deception from an interdependence/game theoretic perspective. Further, we develop and experimentally investigate an algorithm capable of indicating whether or not a particular social situation warrants deception on the part of the robot. Our qualitative and quantitative results provide evidence that, indeed, our algorithm recognizes situations which justify deception and that a robot capable of discerning these situations is better suited to act than one that does not.