arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05010cs.ROcs.HC
收藏

信号还是噪声:真实世界中人类对机器人错误的反应

Signal or 'Noise': Human Reactions to Robot Errors in the Wild

Maia Stiber, Sameer Khan, Russell Taylor, Chien-Ming Huang

AI总结:

研究探讨了真实世界中人类对机器人错误的社会反应,发现社会信号在现实环境中丰富但嘈杂,为真实场景下的人机交互提供了新的见解。

摘要:

在现实世界中,机器人经常出现错误,但人们对非实验室环境中错误的社会反应知之甚少。先前的研究表明,在受限互动中,社会信号在错误管理中是可靠且有用的,但不清楚这种可靠性是否适用于现实世界——尤其是当非社会机器人在重复和群体互动中出现连续或传播性错误时。为此,我们构建了一个咖啡机器人并进行了公开的实地部署(N=49)。我们发现参与者对错误和其他刺激的反应中表现出多样化的社会信号,特别是在群体互动中。我们的发现表明,在现实世界中,社会信号丰富(参与者主动提供关于互动的信息),但“嘈杂”。我们讨论了在现实世界人机交互中使用社会信号的教训、益处和挑战。

英文摘要:

In the real world, robots frequently make errors, yet little is known about people's social responses to errors outside of lab settings. Prior work has shown that social signals are reliable and useful for error management in constrained interactions, but it is unclear if this holds in the real world - especially with a non-social robot in repeated and group interactions with successive or propagated errors. To explore this, we built a coffee robot and conducted a public field deployment ($N = 49$). We found that participants consistently expressed varied social signals in response to errors and other stimuli, particularly during group interactions. Our findings suggest that social signals in the wild are rich (with participants volunteering information about the interaction), but "noisy." We discuss lessons, benefits, and challenges for using social signals in real-world HRI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑