Neural Network Control of a Pneumatic Robot Arm

Ted Hesselroth, Kakali Sarkar, Klaus Schulten, P. Patrick van der Smagt

Research output: Contribution to journalArticlepeer-review

Abstract

A neural map algorithm has been employed to control a five joint pneumatic robot arm and gripper through feedback from two video cameras. The pneumatically driven robot arm employed in this investigation shares essential mechanical characteristices with skeletal muscle systems. To control the position of the arm, 200 neurons formed a netwrok representing the three-dimensional workspace embedded in a four dimensional system of coordinates from the two cameras, and learned a threee dimensional set of pressures corresponding to the end effector positions, as well as a set of 3X4 Jacobian matrices for interpolating between these positions.

Original languageEnglish (US)
Pages (from-to)28-38
Number of pages11
JournalIEEE Transactions on Systems, Man and Cybernetics
Volume24
Issue number1
DOIs
StatePublished - Jan 1 1994

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Neural Network Control of a Pneumatic Robot Arm'. Together they form a unique fingerprint.

Cite this