Multi-Layer Perceptrons for Task Visual Servoing in Robotics - Université de Bretagne Occidentale Access content directly
Book Sections Year : 1996

Multi-Layer Perceptrons for Task Visual Servoing in Robotics

Abstract

A six-degree-of-freedom robot with a CCD-camera mounted on its end-effector is operated in a closed loop control system. The aim is to servo the camera on an object which moves freely in 3D space (translation + rotation), so that the image of the object on the camera screen is always the “reference image”, defined by an arbitrary reference position of the object with respect to the camera. Classical mechanics equations are first studied in order to determine the significant parameters of the problem. Then, a control system based on the use of a MultiLayer Perceptron (MLP) is built. Results and comparisons detailing the behavior of the system in different cases (uniform and non-uniform translations and rotations of the object) are presented, and show the interest of the approach vs. classical methods.
Fichier principal
Vignette du fichier
1996_05_scitec_robot.pdf (383.87 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Licence
Copyright

Dates and versions

hal-03222621 , version 1 (01-04-2023)

Licence

Copyright

Identifiers

  • HAL Id : hal-03222621 , version 1

Cite

Nadine Rondel, Gilles Burel. Multi-Layer Perceptrons for Task Visual Servoing in Robotics. Nuno J. Mamede and Carlos Pinto-Ferreira. Applications of Artificial Intelligence – Expert Systems, Robots and Vision Systems, Fuzzy Logic and Neural Networks, Trans Tech Publications Ltd, 1996, 3-9084-5017-9. ⟨hal-03222621⟩
29 View
4 Download

Share

Gmail Mastodon Facebook X LinkedIn More