Identification of Constrained Robot Dynamics Using Dynamic Neural Networks

E. B. Kosmatopoulos and M. A. Christodoulou
Additional contact information
E. B. Kosmatopoulos: Technical University of Crete, Dept. of Electronic & Computer Engineering
M. A. Christodoulou: Technical University of Crete, Dept. of Electronic & Computer Engineering

A chapter in Advances in Stochastic Modelling and Data Analysis, 1995, pp 384-412 from Springer

Abstract: Abstract It is nowadays well known that neural networks can model nonlinear dynamical systems. This paper solves an identification problem of a robot manipulator which is moving on a constraint surface, by using dynamical neural networks. More explicitly we use Differential/Algebraic Recurrent High Order Neural Networks (D/A-RHONNs) with a learning algorithm which is based on Lyapunov stability theory. The network consists of a combination of differential algebraic equations, and this property makes it effective in identifying nonlinear differential/algebraic systems. Simulation results demonstrate the applicability of the approach.

Keywords: Constraint robot dynamics; differential/algebraic systems; recurrent high order neural networks; nonlinear system identification. (search for similar items in EconPapers)
Date: 1995
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-94-017-0663-6_23

Ordering information: This item can be ordered from
http://www.springer.com/9789401706636

DOI: 10.1007/978-94-017-0663-6_23

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().