Explain yourself! Effects of Explanations in Human-Robot Interaction

TL;DR

This study investigates how explanations from robots influence human perceptions during interaction, finding explanations increase perceived liveliness and human-likeness but do not affect perceived competence or safety.

Contribution

It provides empirical evidence on the effects of robot explanations in human-robot interaction, highlighting their impact on perceived liveliness and human-likeness.

Findings

Explanations increase perceived liveliness.

Explanations increase perceived human-likeness.

Explanations do not significantly affect perceived competence or safety.

Abstract

Recent developments in explainable artificial intelligence promise the potential to transform human-robot interaction: Explanations of robot decisions could affect user perceptions, justify their reliability, and increase trust. However, the effects on human perceptions of robots that explain their decisions have not been studied thoroughly. To analyze the effect of explainable robots, we conduct a study in which two simulated robots play a competitive board game. While one robot explains its moves, the other robot only announces them. Providing explanations for its actions was not sufficient to change the perceived competence, intelligence, likeability or safety ratings of the robot. However, the results show that the robot that explains its moves is perceived as more lively and human-like. This study demonstrates the need for and potential of explainable human-robot interaction and the wider assessment of its effects as a novel research direction.