Neural network architecture for robot hand control
Authors:
- 1 April 1989
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Magazine
- Vol. 9 (3) , 38-43
Abstract
A robot hand control system called GeSAM, which is under development at the University of Southern California, is described. The goal of the GeSAM architecture is to provide a generic robot hand controller that is based on a model of human prehensile function. It focuses on the relationship between geometric object primitives and the ways a hand can perform prehensile behaviors. It is shown how the relationship between object primitives and a useful set of grasp modes can be learned by an adaptive neural network. By adding training points as necessary, system performance can be improved, avoiding the tedious job of computing every relationship individually.Keywords
This publication has 7 references indexed in Scilit:
- Shape description and grasping for robot hand-eye coordinationIEEE Control Systems Magazine, 1989
- Design of tactile sensing systems for dextrous manipulatorsIEEE Control Systems Magazine, 1988
- Functional Hand Evaluations: A ReviewAmerican Journal of Occupational Therapy, 1987
- Modeling manufacturing grips and correlations with the design of robotic hands1986
- Opposition Space as a Structuring Concept for the Analysis of Skilled Hand Movements1986
- Coordinated Control Programs for Movements of the Hand1985
- THE PREHENSILE MOVEMENTS OF THE HUMAN HANDThe Journal of Bone and Joint Surgery. British volume, 1956