Home // ACHI 2020, The Thirteenth International Conference on Advances in Computer-Human Interactions // View article

Enhancing Human Trust and Perception of Robots Through Explanations

Authors:
Misbah Javaid
Vladimir Estivill-Castro
Rene Hexel

Keywords: Implicit Trust; Explicit Trust; Explanations; Human-Robot Physical Interaction.

Abstract:
In order to integrate robots into human-environment, robots need to make their decison-making transparent to the outside world, to upraise human’s stakes of trusting the robots. In this manner, explanations from a robot is a promising way to express “how” a decision is made and “why” the decision-made is best among all other decisions. In this paper, we contribute to a user study investigating the effect of robot’s explanations on human’s trust during an interactive, game-playing environment, in which a robot plays partial information game Domino with humans in teams. The robot plays two roles i.e., a team partner with a human and an adversary with two humans and communicates through explanations in human understandable-terms. Explanations from the robot not only provide insight into its decision-making process but also explains to a human how to play the game that helps in improving humans’ learning of the task domain. We evaluated human participants’ implicit trust on the robot by observing their way of playing the game (i.e. cooperation and sacrifice towards their robot teammate) and used questionnaires to measure participants’ explicit trust and change in subjective perception of the robot. Our results suggest that human participants perceived the robot with explanations capability as a trustworthy teammate. We conclude that explanations can be generally used as an effective communication modality for robots to earn human trust on them in the social environment.

Pages: 172 to 181

Copyright: Copyright (c) IARIA, 2020

Publication date: March 22, 2020

Published in: conference

ISSN: 2308-4138

ISBN: 978-1-61208-761-0

Location: Valencia, Spain

Dates: from November 21, 2020 to November 25, 2020