Sciweavers

Share
ICPR
2004
IEEE

Periodic Nonlinear Principal Component Neural Networks for Humanoid Motion Segmentation, Generalization, and Generation

9 years 6 months ago
Periodic Nonlinear Principal Component Neural Networks for Humanoid Motion Segmentation, Generalization, and Generation
In an experiment with a soccer playing robot, periodic temporally-constrained nonlinear principal component neural networks (NLPCNNs) are shown to characterize humanoid motion effectively by exploiting fundamental sensorimotor relationships. Each network learns a periodic or transitional trajectory in a phase space of possible acnd thus abstracts a kind of protosymbol. NLPCNNs can play a key role in a system that learns to imitate people, enabling a robot to recognize the behavior of others because it has grounded that behavior in terms of its own bodily movements.
Karl F. MacDorman, Rawichote Chalodhorn, Minoru As
Added 09 Nov 2009
Updated 09 Nov 2009
Type Conference
Year 2004
Where ICPR
Authors Karl F. MacDorman, Rawichote Chalodhorn, Minoru Asada
Comments (0)
books