Original Contribution: Recognition of manipulated objects by motor learning with modular architecture networks

Authors:
Hiroaki Gomi;Mitsuo Kawato
Affiliations:
-;-
Venue:
Neural Networks
Year:
1993

Citing 5
Cited 6

Robotic object recognition using vision and touch

Robotic object recognition using vision and touch
Connectionist learning for control: an overview

Neural networks for control
Learning trajectory and force control of an artificial muscle arm by parallel-hierarchical neural network model

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
A competitive modular connectionist architecture

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Evaluation of adaptive mixtures of competing experts

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3

Multiple model-based reinforcement learning

Neural Computation
Learning to generate articulated behavior through the bottom-up and the top-down interaction processes

Neural Networks
MOSAIC Model for Sensorimotor Learning and Control

Neural Computation
An internal model for acquisition and retention of motor learning during arm reaching

Neural Computation
Modular learning schemes for visual robot control

Biomimetic Neural Learning for Intelligent Robots
Extraction of primitive representation from captured human movements and measured ground reaction force to generate physically consistent imitated behaviors

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

For recognition and control of multiple manipulated objects, we present two learning schemes for neuralnetwork controllers based on feedback-error-learning and modular architecture. In both schemes, the network consists of a recognition network and modular control networks. In the first scheme, a Gating Network is trained to acquire object-specific representations for recognition of a number of objects (or sets of objects). In the second scheme, an Estimation Network is trained to acquire function-specific, rather than object-specific, representations which directly estimate physical parameters. Both recognition networks are trained to identify manipulated objects using somatic and/or visual information. After learning, appropriate motor commands for manipulation of each object are issued by the control networks which have a modular structure. By simulation of simple examples, the potential advantages and disadvantages of the two schemes are examined.