Teaching Emotion Expressions to a Human Companion Robot using Deep Neural Architectures

International Joint Conference on Neural Networks (IJCNN), pages 627--634, doi:10.1109/IJCNN.2017.7965911 - May 2017.
Associated documents : Churamani-Teaching_EMotion_Expressions_2017-Webpage-NC.pdf [3.3Mo]   http://dx.doi.org/10.1109/IJCNN.2017.7965911
Human companion robots need to be sociable and responsive towards emotions to better interact with the human environment they are expected to operate in. This paper is based on the Neuro-Inspired COmpanion robot (NICO) and investigates a hybrid, deep neural network model to teach the NICO to associate perceived emotions with expression representations using its on-board capabilities. The proposed model consists of a Convolutional Neural Network (CNN) and a Self-organising Map (SOM) to perceive the emotions expressed by a human user towards NICO and trains two parallel Multilayer Perceptron (MLP) networks to learn general as well as person-specific associations between perceived emotions and the robot's facial expressions.

 

@InProceedings\{CKSBW17,
  author       = "Churamani, Nikhil and Kerzel, Matthias and Strahl, Erik and Barros, Pablo and Wermter, Stefan",
  title        = "Teaching Emotion Expressions to a Human Companion Robot using Deep Neural Architectures",
  booktitle    = "International Joint Conference on Neural Networks (IJCNN)",
  pages        = "627--634",
  month        = "May",
  year         = "2017",
  publisher    = "IEEE",
  address      = "Anchorage, Alaska",
  key          = "Churamani2017Teaching",
  doi          = "10.1109/IJCNN.2017.7965911",
  url          = "https://www2.informatik.uni-hamburg.de/wtm/publications/2017/CKSBW17/"
}

» Nikhil Churamani
» Matthias Kerzel
» Erik Strahl
» Pablo Barros
» Stefan Wermter