文章基本信息

标题：Building Model to Predict How Likely User is to Talk to Humanoid Robot
本地全文：下载
作者：Takaaki Sugiyama ; Kazunori Komatani ; Satoshi Sato 等
期刊名称：人工知能学会論文誌
印刷版ISSN：1346-0714
电子版ISSN：1346-8030
出版年度：2013
卷号：28
期号：3
页码：255-260
DOI：10.1527/tjsai.28.255
出版社：The Japanese Society for Artificial Intelligence
摘要：We tackle a novel problem to predict how likely a humanoid robot is to be talked by a user. A human speaker usually takes his/her addressee's state into consideration and chooses when to talk to the addressee; this convention can be used when a system interprets its audio input. We formulate this problem by using machine learning whose input features are a humanoid's behaviors such as its posture, motion, and utterrance. A possible application of the model is to reject environmental noises that occur at timing when a cooperative user hardly talks to a robot.
关键词：human-robot interaction ; humanoid robot ; machine learning