arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.00262cs.ROcs.HC
收藏

为何是面孔?

"Why the face?": Exploring Robot Error Detection Using Instrumented Bystander Reactions

Cornell University, Cornell Tech(康奈尔大学,康奈尔科技);Cornell University(康奈尔大学);Accenture Labs(埃森哲实验室)

Maria Teresa Parreira, Ruidong Zhang, Sukruth Gowdru Lingaraju, Alexandra Bremers, Xuanyu Fang, Adolfo Ramirez-Aristizabal, Manaswi Saha, Michael Kuniavsky, Cheng Zhang, Wendy Ju

AI总结:

本文提出通过颈部装置捕捉面部表情,开发NeckNet-18模型实现机器人错误检测,提升社交互动能力。

摘要:

人类如何识别并纠正社交失误?我们通过观察同伴,解码旁观者细微的提示(如抬眉、大笑)来评估环境和自身行为,从而获得社交能力。然而,机器人在感知和利用这些细微反应方面存在困难。通过使用一种新型的颈部装置,该装置记录下巴区域的面部表情,我们探索了此前未被利用的数据来捕捉和解读人类对机器人错误的反应的潜力。首先,我们开发了NeckNet-18,一个3D面部重建模型,用于将通过下巴相机捕捉到的反应映射到面部点和头部运动。随后,我们利用这些面部反应开发了一个机器人错误检测模型,其性能优于标准方法,如使用OpenFace或视频数据,特别是在同一个人数据中表现良好。通过这项工作,我们主张扩展人机协同的机器人感知,促进机器人在多样化人类环境中的无缝整合,推动社交提示检测的边界,开辟适应性机器人学的新途径。

英文摘要:

How do humans recognize and rectify social missteps? We achieve social competence by looking around at our peers, decoding subtle cues from bystanders - a raised eyebrow, a laugh - to evaluate the environment and our actions. Robots, however, struggle to perceive and make use of these nuanced reactions. By employing a novel neck-mounted device that records facial expressions from the chin region, we explore the potential of previously untapped data to capture and interpret human responses to robot error. First, we develop NeckNet-18, a 3D facial reconstruction model to map the reactions captured through the chin camera onto facial points and head motion. We then use these facial responses to develop a robot error detection model which outperforms standard methodologies such as using OpenFace or video data, generalizing well especially for within-participant data. Through this work, we argue for expanding human-in-the-loop robot sensing, fostering more seamless integration of robots into diverse human environments, pushing the boundaries of social cue detection and opening new avenues for adaptable robotics.

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。

↑