A Convergence of Decision-making Criterions in a Human-robot Group

- The Robot Makes a Suitable Decision-making Criterion by Interacting with the Group Members -

Abstract

This paper presents a model to enable robots to create a suitable criterion for decision-making by indirectly interacting with people in a group. Using this model, a robot learns a suitable criterion for the group as a group member through reinforcement learning. When people, who have different personalities form a group, they adjust their criteria to a common criterion for the group. The present study investigates whether the robot can make a suitable decision-making criterion in a group by learning from interactions. Participants and the robot answer easy quizzes that have vague questions without direct conversation. Our experiments reveal that a group consisting of the participants and the robot forms a common criterion in a limited scenario. However, further study is required to reveal a robot’s social influence of human.