Achieving Synergy in Cognitive Behavior of Humanoids via Deep Learning of Dynamic Visuo-Motor-Attentional Coordination
Authors:
Preprint
Abstract
The current study examines how adequate coordination among different cognitive processes including visual recognition, attention switching, action preparation and generation can be developed via learning of robots by introducing a novel model, the Visuo-Motor Deep Dynamic Neural Network (VMDNN). The proposed model is built on coupling of a dynamic vision network, a motor generation network, and a higher level network allocated on top of these two. The simulation experiments using the iCub simulator were conducted for cognitive tasks including visual object manipulation responding to human gestures. The results showed that synergetic coordination can be developed via iterative learning through the whole network when spatio-temporal hierarchy and temporal one can be self-organized in the visual pathway and in the motor pathway, respectively, such that the higher level can manipulate them with abstraction.Keywords
All Related Versions
- Version 1, 2015-07-09, ArXiv
- Published version: , 817.
This publication has 6 references indexed in Scilit:
- Self-Organization of Spatio-Temporal Hierarchy via Learning of Dynamic Visual Image Patterns on Action SequencesPLOS ONE, 2015
- Self-Organization and Compositionality in Cognitive Brains: A Neurorobotics StudyProceedings of the IEEE, 2014
- Emergence of Functional Hierarchy in a Multiple Timescale Neural Network Model: A Humanoid Robot ExperimentPLOS Computational Biology, 2008
- iCub: the design and realization of an open humanoid platform for cognitive and neuroscience researchAdvanced Robotics, 2007
- Slow Feature Analysis: Unsupervised Learning of InvariancesNeural Computation, 2002
- Emergence of simple-cell receptive field properties by learning a sparse code for natural imagesNature, 1996