COOPERATIVE CONTROL OF 2 DIRECT-DRIVE ROBOTS USING NEURAL NETWORKS (GRASPING AND MOVEMENT OF AN OBJECT)

Authors
Citation
Yy. Hwang et I. Todo, COOPERATIVE CONTROL OF 2 DIRECT-DRIVE ROBOTS USING NEURAL NETWORKS (GRASPING AND MOVEMENT OF AN OBJECT), JSME international journal. Series C, dynamics, control, robotics, design and manufacturing, 37(2), 1994, pp. 335-341
Citations number
14
Categorie Soggetti
Engineering, Mechanical
ISSN journal
13408062
Volume
37
Issue
2
Year of publication
1994
Pages
335 - 341
Database
ISI
SICI code
1340-8062(1994)37:2<335:CCO2DR>2.0.ZU;2-A
Abstract
A learning control algorithm using neural networks is proposed for gra sping and movement of an object by a pair of direct-drive (DD) robots with two degrees of freedom. The proposed algorithm has three feedback controllers and two neural networks. After the completion of learning , the outputs of the feedback controllers are nearly equal to zero, an d the two neural networks play an important role in the control system . Therefore, the optimum setting of control parameters is unnecessary. In other words, the proposed algorithm does not necessitate any knowl edge of the controlled system in advance. The effectiveness of the pro posed algorithm is demonstrated by the experiment on the cooperative c ontrol of the parallelogram-type DD robots. It is also shown that the force of gravity can be compensated by this algorithm.