On-the-Fly Detection of User Engagement Decrease in Spontaneous Human–Robot Interaction Using Recurrent and Deep Neural Networks
On-the-Fly Detection of User Engagement Decrease in Spontaneous Human–Robot Interaction Using Recurrent and Deep Neural Networks
复制标题
使用递归和深度神经网络实时检测自发人机交互中的用户参与度下降
DOI：
10.1007/s12369-019-00591-2
复制
发表时间：
2019
影响因子：
4.7
通讯作者：
C. Clavel
中科院分区：
文献类型：
--
作者：
Atef Ben Youssef;G. Varni;S. Essid;C. Clavel
在本文中，我们考虑检测的参与度下降的用户自发地与社会辅助机器人在公共空间中进行交互。我们首先描述了UE-HRI数据集，它收集自发的人机交互，遵循情感计算研究社区提供的指南，以收集“野外”数据。然后，我们分析了用户的行为，重点是在与机器人交互过程中的表情，凝视，头部运动，面部表情和语音。最后，我们研究了使用深度学习技术（递归和深度神经网络）来实时检测用户参与度的下降。这项工作的结果突出，特别是考虑到用户的行为的时间动态的相关性。允许1-2秒作为缓冲延迟提高了对用户参与做出决定的性能。
In this paper we consider the detection of a decrease of engagement by users spontaneously interacting with a socially assistive robot in a public space. We first describe the UE-HRI dataset that collects spontaneous human–robot interactions following the guidelines provided by the affective computing research community to collect data “in-the-wild”. We then analyze the users’ behaviors, focusing on proxemics, gaze, head motion, facial expressions and speech during interactions with the robot. Finally, we investigate the use of deep leaning techniques (recurrent and deep neural networks) to detect user engagement decrease in real-time. The results of this work highlight, in particular, the relevance of taking into account the temporal dynamics of a user’s behavior. Allowing 1–2 s as buffer delay improves the performance of taking a decision on user engagement.