Decision-Making of Communication Robots Through Robot Ethics

Abstract

With the recent developments in robotics, the ability of robots to recognize their environment has significantly improved. However, the manner in which robots behave depending on a particular situation remains an unsolved problem. In this study, we propose a decision-making method for robots based on robot ethics. Specifically, we applied the two-level theory of utilitarianism, comprising SYSTEM 1 (intuitive level) for quick decisions and SYSTEM 2 (critical level) for slow but careful decisions. SYSTEM 1 represented a set of heuristically determined responses and SYSTEM 2 represented a rule-based discriminator. The decision-making method was as follows. First, SYSTEM 1 selected the response to the input. Next, SYSTEM 2 selected the rule that the robot’s behavior should follow depending on the amount of happiness and unhappiness of the human, robot, situation, and society. We assumed three choices for SYSTEM 2. We assigned “non-cooperation” to asocial comments, “cooperation” to when the amount of happiness was considered to be high beyond the status quo bias, and “withholding” to all other cases. In the case of choosing between cooperation or non-cooperation, we modified the behavior selected in SYSTEM 1. An impression evaluation experiment was conducted, and the effectiveness of the proposed method was demonstrated.