I Need Your Advice... Human Perceptions of Robot Moral Advising\n Behaviors

摘要

Due to their unique persuasive power, language-capable robots must be able to\nboth act in line with human moral norms and clearly and appropriately\ncommunicate those norms. These requirements are complicated by the possibility\nthat humans may ascribe blame differently to humans and robots. In this work,\nwe explore how robots should communicate in moral advising scenarios, in which\nthe norms they are expected to follow (in a moral dilemma scenario) may be\ndifferent from those their advisees are expected to follow. Our results suggest\nthat, in fact, both humans and robots are judged more positively when they\nprovide the advice that favors the common good over an individual's life. These\nresults raise critical new questions regarding people's moral responses to\nrobots and the design of autonomous moral agents.\n