Imitating by Generating: Deep Generative Models for Imitation of Interactive Tasks

Imitating by Generating: Deep Generative Models for Imitation of Interactive Tasks

To coordinate actions with an interaction partner requires a constant exchange of sensorimotor signals. Humans acquire these skills in infancy and early childhood mostly by imitation learning and active engagement with a skilled partner. They require the ability to predict and adapt to one's pa...

Full description

Bibliographic Details
Main Authors: Judith Bütepage, Ali Ghadirzadeh, Özge Öztimur Karadaǧ, Mårten Björkman, Danica Kragic
Format: Article
Language:English
Published: Frontiers Media S.A. 2020-04-01
Series:Frontiers in Robotics and AI
Subjects:
imitation learning
human-robot interaction
generative models
deep learning
sensorimotor coordination
variational autoencoders
Online Access:https://www.frontiersin.org/article/10.3389/frobt.2020.00047/full

Internet

https://www.frontiersin.org/article/10.3389/frobt.2020.00047/full

Similar Items