Dynamics model abstraction scheme using radial basis functions

Authors:
Silvia Tolu;Mauricio Vanegas;Rodrigo Agís;Richard Carrillo;Antonio Cañas
Affiliations:
Department of Computer Architecture and Technology, CITIC ETSI Informática y de Telecomunicación, University of Granada, Spain;Department of Biophysical and Electronic Engineering, University of Genoa, Italy;Department of Computer Architecture and Technology, CITIC ETSI Informática y de Telecomunicación, University of Granada, Spain;Department of Computer Architecture and Technology, CITIC ETSI Informática y de Telecomunicación, University of Granada, Spain;Department of Computer Architecture and Technology, CITIC ETSI Informática y de Telecomunicación, University of Granada, Spain
Venue:
Journal of Control Science and Engineering - Special issue on Dynamic Neural Networks for Model-Free Control and Identification
Year:
2012

Citing 24
Cited 0

Estimation of inertial parameters of manipulator loads and links

International Journal of Robotics Research
Neural networks for control systems: a survey

Automatica (Journal of IFAC)
Multiple paired forward and inverse models for motor control

Neural Networks - Special issue on neural control and robotics: biology and technology
A Multilayer Perceptrons Model for the Stability of a Bipedal Robot

Neural Processing Letters
Fundamentals of Robotics: Analysis and Control

Fundamentals of Robotics: Analysis and Control
Fundamentals of Artificial Neural Networks

Fundamentals of Artificial Neural Networks
Statistical Learning for Humanoid Robots

Autonomous Robots
Modeling of Robot Dynamics Based on a Multi-Dimensional RBF-Like Neural Network

ICIIS '99 Proceedings of the 1999 International Conference on Information Intelligence and Systems
Control of a robot manipulator and pendubot system using artificial neural networks

Robotica
Incremental Online Learning in High Dimensions

Neural Computation
MOSAIC Model for Sensorimotor Learning and Control

Neural Computation
PD Control of robot with velocity estimation and uncertainties compensation

International Journal of Robotics and Automation
Learning Robot Dynamics for Computed Torque Control Using Local Gaussian Processes Regression

LAB-RS '08 Proceedings of the 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems
Local Dimensionality Reduction for Non-Parametric Regression

Neural Processing Letters
Learning Dynamic Obstacle Avoidance for a Robot Arm Using Neuroevolution

Neural Processing Letters
Sequential Adaptive Fuzzy Inference System (SAFIS) for nonlinear system identification and prediction

Fuzzy Sets and Systems
Bio-inspired control model for object manipulation by humanoid robots

IWANN'07 Proceedings of the 9th international work conference on Artificial neural networks
Learning multiple models of non-linear dynamics for control under varying contexts

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
Variable neural networks for adaptive control of nonlinear systems

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Robust radial basis function neural networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Solving function distribution and behavior design problem for cooperative object handling by multiple mobile robots

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Cerebellar Input Configuration Toward Object Model Abstraction in Manipulation Tasks

IEEE Transactions on Neural Networks
Fuzzily Connected Multimodel Systems Evolving Autonomously From Data Streams

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Cerebellarlike Corrective Model Inference Engine for Manipulation Tasks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a control model for object manipulation. Properties of objects and environmental conditions influence the motor control and learning. System dynamics depend on an unobserved external context, for example, work load of a robot manipulator. The dynamics of a robot arm change as it manipulates objects with different physical properties, for example, the mass, shape, or mass distribution. We address active sensing strategies to acquire object dynamical models with a radial basis function neural network (RBF). Experiments are done using a real robot's arm, and trajectory data are gathered during various trials manipulating different objects. Biped robots do not have high force joint servos and the control system hardly compensates all the inertia variation of the adjacent joints and disturbance torque on dynamic gait control. In order to achieve smoother control and lead tomore reliable sensorimotor complexes, we evaluate and compare a sparse velocity-driven versus a dense position-driven control scheme.