Demonstrating MoveAE: Modifying Affective Robot Movements Using Classifying Variational Autoencoders

被引：0

作者：

Suguitan, Michael ^{[1
]}

Gomez, Randy ^{[2
]}

Hoffman, Guy ^{[1
]}

机构：

[1] Cornell Univ, HRC2 Lab, Ithaca, NY 14853 USA

[2] Honda Res Inst Japan, Wako, Saitama, Japan

来源：

HRI'20: COMPANION OF THE 2020 ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION | 2020年

关键词：

Social robots; deep learning; neural networks; affective generation;

D O I：

10.1145/3371382.3378202

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

We developed a method for modifying emotive robot movements with a reduced dependency on domain knowledge by using neural networks. We use hand-crafted movements for a Blossom robot and a classifying variational autoencoder to adjust affective movement features by using simple arithmetic in the network's learned latent embedding space. We will demonstrate the workflow of using a graphical interface to modify the valence and arousal of movements. Participants will be able to use the interface themselves and watch Blossom perform the modified movements in real time.

引用

页码：78 / 78

页数：1