Sciweavers

959 search results - page 19 / 192
» Modeling Sensorimotor Learning with Linear Dynamical Systems
Sort
View
CVPR
2005
IEEE
14 years 9 months ago
Modeling Dynamic Scenes with Active Appearance
In this work we propose a model for video scenes that contain temporal variability in shape and appearance. We propose a conditionally linear model akin to a dynamic extension of ...
Gianfranco Doretto
ICONIP
2010
13 years 6 months ago
Learning Basis Representations of Inverse Dynamics Models for Real-Time Adaptive Control
Abstract. In this paper, we propose a novel approach for adaptive control of robotic manipulators. Our approach uses a representation of inverse dynamics models learned from a vari...
Yasuhito Horiguchi, Takamitsu Matsubara, Masatsugu...
ICINCO
2004
153views Robotics» more  ICINCO 2004»
13 years 9 months ago
Iterative Linear Quadratic Regulator Design for Nonlinear Biological Movement Systems
This paper presents an Iterative Linear Quadratic Regulator (ILQR) method for locally-optimal feedback control of nonlinear dynamical systems. The method is applied to a musculo-s...
Weiwei Li, Emanuel Todorov
IJCNN
2006
IEEE
14 years 1 months ago
Venn-like models of neo-cortex patches
— This work presents a new architecture of artificial neural networks – Venn Networks, which produce localized activations in a 2D map while executing simple cognitive tasks. T...
Fernando Buarque de Lima Neto, Philippe De Wilde
ICRA
2008
IEEE
150views Robotics» more  ICRA 2008»
14 years 2 months ago
A Bayesian approach to empirical local linearization for robotics
— Local linearizations are ubiquitous in the control of robotic systems. Analytical methods, if available, can be used to obtain the linearization, but in complex robotics system...
Jo-Anne Ting, Aaron D'Souza, Sethu Vijayakumar, St...