Toward Ethical Robotic Behavior in Human-Robot Interaction Scenarios

TL;DR

This paper explores developing an ethical architecture for robots by surveying human and expert perspectives on ethical behavior in specific scenarios, aiming to inform robot decision-making aligned with human morals.

Contribution

It introduces a framework integrating human and formal ethical perspectives to guide robot behavior in human-robot interactions.

Findings

Most ethical frameworks and folk morality are conservative about deception in high-risk tasks.

Humans and experts show differing views on ethical decision-making in scenarios.

Formal ethical frameworks influence robot behavior to align with human moral standards.

Abstract

This paper describes current progress on developing an ethical architecture for robots that are designed to follow human ethical decision-making processes. We surveyed both regular adults (folks) and ethics experts (experts) on what they consider to be ethical behavior in two specific scenarios: pill-sorting with an older adult and game playing with a child. A key goal of the surveys is to better understand human ethical decision-making. In the first survey, folk responses were based on the subject's ethical choices ("folk morality"); in the second survey, expert responses were based on the expert's application of different formal ethical frameworks to each scenario. We observed that most of the formal ethical frameworks we included in the survey (Utilitarianism, Kantian Ethics, Ethics of Care and Virtue Ethics) and "folk morality" were conservative toward deception in the high-risk task with an older adult when both the adult and the child had significant performance deficiencies.