Cargando…
Acquisition of Viewpoint Transformation and Action Mappings via Sequence to Sequence Imitative Learning by Deep Neural Networks
We propose an imitative learning model that allows a robot to acquire positional relations between the demonstrator and the robot, and to transform observed actions into robotic actions. Providing robots with imitative capabilities allows us to teach novel actions to them without resorting to trial-...
Autores principales: | Nakajo, Ryoichi, Murata, Shingo, Arie, Hiroaki, Ogata, Tetsuya |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6066551/ https://www.ncbi.nlm.nih.gov/pubmed/30087605 http://dx.doi.org/10.3389/fnbot.2018.00046 |
Ejemplares similares
-
Representation Learning of Logic Words by an RNN: From Word Sequences to Robot Actions
por: Yamada, Tatsuro, et al.
Publicado: (2017) -
Dynamical Integration of Language and Behavior in a Recurrent Neural Network for Human–Robot Interaction
por: Yamada, Tatsuro, et al.
Publicado: (2016) -
Tool-Use Model to Reproduce the Goal Situations Considering Relationship Among Tools, Objects, Actions and Effects Using Multimodal Deep Neural Networks
por: Saito, Namiko, et al.
Publicado: (2021) -
Neural responses when learning spatial and object sequencing tasks via imitation
por: Renner, Elizabeth, et al.
Publicado: (2018) -
The neural basis of the imitation drive
por: Hanawa, Sugiko, et al.
Publicado: (2016)