Implications of AI Bias in HRI: Risks (and Opportunities) when Interacting with a Biased Robot

IF 4.2 Q2 ROBOTICS

ACM Transactions on Human-Robot Interaction Pub Date : 2023-03-13 DOI:10.1145/3568162.3576977

Tom Hitron, Noa Morag Yaar, H. Erel

{"title":"Implications of AI Bias in HRI: Risks (and Opportunities) when Interacting with a Biased Robot","authors":"Tom Hitron, Noa Morag Yaar, H. Erel","doi":"10.1145/3568162.3576977","DOIUrl":null,"url":null,"abstract":"Social robotic behavior is commonly designed using AI algorithms which are trained on human behavioral data. This training process may result in robotic behaviors that echo human biases and stereotypes. In this work, we evaluated whether an interaction with a biased robotic object can increase participants' stereotypical thinking. In the study, a gender-biased robot moderated debates between two participants (man and woman) in three conditions: (1) The robot's behavior matched gender stereotypes (Pro-Man); (2) The robot's behavior countered gender stereotypes (Pro-Woman); (3) The robot's behavior did not reflect gender stereotypes and did not counter them (No-Preference). Quantitative and qualitative measures indicated that the interaction with the robot in the Pro-Man condition increased participants' stereotypical thinking. In the No-Preference condition, stereotypical thinking was also observed but to a lesser extent. In contrast, when the robot displayed counter-biased behavior in the Pro-Woman condition, stereotypical thinking was eliminated. Our findings suggest that HRI designers must be conscious of AI algorithmic biases, as interactions with biased robots can reinforce implicit stereotypical thinking and exacerbate existing biases in society. On the other hand, counter-biased robotic behavior can be leveraged to support present efforts to address the negative impact of stereotypical thinking.","PeriodicalId":36515,"journal":{"name":"ACM Transactions on Human-Robot Interaction","volume":"64 1","pages":""},"PeriodicalIF":4.2000,"publicationDate":"2023-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Human-Robot Interaction","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3568162.3576977","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ROBOTICS","Score":null,"Total":0}

引用次数: 3

Abstract

Social robotic behavior is commonly designed using AI algorithms which are trained on human behavioral data. This training process may result in robotic behaviors that echo human biases and stereotypes. In this work, we evaluated whether an interaction with a biased robotic object can increase participants' stereotypical thinking. In the study, a gender-biased robot moderated debates between two participants (man and woman) in three conditions: (1) The robot's behavior matched gender stereotypes (Pro-Man); (2) The robot's behavior countered gender stereotypes (Pro-Woman); (3) The robot's behavior did not reflect gender stereotypes and did not counter them (No-Preference). Quantitative and qualitative measures indicated that the interaction with the robot in the Pro-Man condition increased participants' stereotypical thinking. In the No-Preference condition, stereotypical thinking was also observed but to a lesser extent. In contrast, when the robot displayed counter-biased behavior in the Pro-Woman condition, stereotypical thinking was eliminated. Our findings suggest that HRI designers must be conscious of AI algorithmic biases, as interactions with biased robots can reinforce implicit stereotypical thinking and exacerbate existing biases in society. On the other hand, counter-biased robotic behavior can be leveraged to support present efforts to address the negative impact of stereotypical thinking.

查看原文本刊更多论文

人工智能偏见在HRI中的含义:与有偏见的机器人互动时的风险(和机遇)

社交机器人的行为通常是用人工智能算法设计的，这些算法是根据人类行为数据训练的。这种训练过程可能会导致机器人的行为与人类的偏见和刻板印象相呼应。在这项工作中，我们评估了与有偏见的机器人物体的互动是否会增加参与者的刻板思维。在研究中，一个性别偏见的机器人在三种情况下主持两名参与者(男性和女性)之间的辩论:(1)机器人的行为符合性别刻板印象(亲男);(2)机器人的行为打破了性别刻板印象(Pro-Woman);(3)机器人的行为不反映性别刻板印象，也不对抗性别刻板印象(No-Preference)。定量和定性测量表明，亲人条件下与机器人的互动增加了被试的刻板思维。在无偏好条件下，也观察到刻板思维，但程度较轻。相比之下，当机器人在亲女性条件下表现出反偏见行为时，刻板印象被消除了。我们的研究结果表明，人力资源研究所的设计者必须意识到人工智能算法的偏见，因为与有偏见的机器人的互动会强化内隐的刻板思维，加剧社会中现有的偏见。另一方面，反偏见的机器人行为可以用来支持当前解决刻板印象思维的负面影响的努力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

ACM Transactions on Human-Robot Interaction Computer Science-Artificial Intelligence

CiteScore

7.70

自引率

5.90%

发文量

期刊介绍： ACM Transactions on Human-Robot Interaction (THRI) is a prestigious Gold Open Access journal that aspires to lead the field of human-robot interaction as a top-tier, peer-reviewed, interdisciplinary publication. The journal prioritizes articles that significantly contribute to the current state of the art, enhance overall knowledge, have a broad appeal, and are accessible to a diverse audience. Submissions are expected to meet a high scholarly standard, and authors are encouraged to ensure their research is well-presented, advancing the understanding of human-robot interaction, adding cutting-edge or general insights to the field, or challenging current perspectives in this research domain. THRI warmly invites well-crafted paper submissions from a variety of disciplines, encompassing robotics, computer science, engineering, design, and the behavioral and social sciences. The scholarly articles published in THRI may cover a range of topics such as the nature of human interactions with robots and robotic technologies, methods to enhance or enable novel forms of interaction, and the societal or organizational impacts of these interactions. The editorial team is also keen on receiving proposals for special issues that focus on specific technical challenges or that apply human-robot interaction research to further areas like social computing, consumer behavior, health, and education.