Discussions About Lying With An Ethical Reasoning Robot

Felix Lindner, Laura Wächter, Martin Mose Bentzen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    Abstract

    The conversational ethical reasoning robot Immanuel is presented. Immanuel is capable of defending multiple ethical views on morally delicate situations. A study was conducted to evaluate the acceptance of Immanuel. The participants had a conversation with the robot on whether lying is permissibile in a given situation. The robot first signaled uncertainty about whether lying is right or wrong in the situation, then disagreed with the participant’s view, and finally asked for justification. The results indicate that participants with a higher tendency to utilitarian judgments are initially more certain about their view as compared to participants with a higher tendency to deontological judgments. These differences vanish at the end of the dialogue. Lying is defended and argued against by both utilitarian and deontologically oriented participants. The diversity of the reported arguments gives an idea of the variety of human moral judgment. Implications for the design and application of morally competent robots are discussed.
    Original languageEnglish
    Title of host publication2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)
    PublisherIEEE
    Publication date2017
    Pages1445-1450
    DOIs
    Publication statusPublished - 2017
    Event26th IEEE International Sympiosium on Robot and Human Interactive Communication - Pestane Palace Hotel, Lisboa, Portugal
    Duration: 28 Aug 20171 Sep 2017

    Conference

    Conference26th IEEE International Sympiosium on Robot and Human Interactive Communication
    LocationPestane Palace Hotel
    CountryPortugal
    CityLisboa
    Period28/08/201701/09/2017

    Fingerprint Dive into the research topics of 'Discussions About Lying With An Ethical Reasoning Robot'. Together they form a unique fingerprint.

    Cite this