Suppr超能文献

机器人与人类面部流线的比较。

Comparison Between the Facial Flow Lines of Androids and Humans.

作者信息

Ishihara Hisashi, Iwanaga Saneyuki, Asada Minoru

机构信息

Graduate School of Engineering, Osaka University, Suita, Japan.

JST Sakigake/Presto, Tokyo, Japan.

出版信息

Front Robot AI. 2021 Mar 22;8:540193. doi: 10.3389/frobt.2021.540193. eCollection 2021.

Abstract

The behavior of an android robot face is difficult to predict because of the complicated interactions between many and various attributes (size, weight, and shape) of system components. Therefore, the system behavior should be analyzed after these components are assembled to improve their performance. In this study, the three-dimensional displacement distributions for the facial surfaces of two android robots were measured for the analysis. The faces of three adult males were also analyzed for comparison. The visualized displacement distributions indicated that the androids lacked two main deformation features observed in the human upper face: curved flow lines and surface undulation, where the upstream areas of the flow lines elevate. These features potentially characterize the human-likeness. These findings suggest that innovative composite motion mechanisms to control both the flow lines and surface undulations are required to develop advanced androids capable of exhibiting more realistic facial expressions. Our comparative approach between androids and humans will improve androids' impressions in future real-life application scenes, e.g., receptionists in hotels and banks, and clerks in shops.

摘要

由于系统组件的许多不同属性(尺寸、重量和形状)之间存在复杂的相互作用,类人机器人面部的行为很难预测。因此,应在这些组件组装后分析系统行为,以提高其性能。在本研究中,为了进行分析,测量了两个类人机器人面部表面的三维位移分布。还分析了三名成年男性的面部以作比较。可视化的位移分布表明,类人机器人缺乏人类上脸观察到的两个主要变形特征:弯曲的流线和表面起伏,其中流线的上游区域会隆起。这些特征可能是类人性的表征。这些发现表明,需要创新的复合运动机制来控制流线和表面起伏,以开发能够展现更逼真面部表情的先进类人机器人。我们在类人机器人和人类之间的比较方法将在未来的现实生活应用场景中改善类人机器人的印象,例如酒店和银行的接待员以及商店的店员。

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验