Document Type

Post-Print

Publication Date

4-2003

Subjects

Neural networks (Computer science), Artificial hands -- Design and construction, Androids, Robots -- Control systems

Abstract

Our goal is to develop the low level control system for an artificial hand ”Blackfingers”. Blackfingers was thought to have two main applications: as humanoid robot’s hand or as a human hand prothesis. In this last application our intent is to realize a device more sophisticated respect the actual commerce prothesis. Also in our intention is to use some biological paradigms to create a human like reflex control easy to be interfaced also with the human nervous system. In this paper we illustrate the properties and the morphology of a human like neural reflex controller, used to set the stiffness and joint positions of our artificial hand. In particular we explain, by simulations results, its ability to emulate the myotatic human reflex, and its capacity to learn in real time the best control strategy.

Description

Originally presented at ICORR 2003, the 8th International Conference on Rehabilitation Robotics, held in Daejeon, Republic of Korea, April 2003, and subsequently included in its proceedings.

Persistent Identifier

http://archives.pdx.edu/ds/psu/12774

Share

COinS