167 articles – 36 Notices  [english version]
HAL : hal-00687644, version 1

Fiche détaillée  Récupérer au format
IROS 2010, Taïwan, Province De Chine (2010)
Stochastic optimization of a neural network-based controller for aggressive maneuvers on loose surfaces
Alexander Terekhov 1, Jean-Baptiste Mouret 1, Christophe Grand 1
(2010)

In this study we develop a feedback controller for a four wheeled autonomous mobile robot. The purpose of the controller is to guarantee robust performance of an aggressive maneuver (90 degrees turn) at high velocity (about 10 m/s) on a loose surface (dirty road). To tackle this highly nonlinear control problem, we employ multi-objective evolutionary algorithms to explore and optimize the parameters of a neural network-based controller. The obtained controller is shown to be robust with respect to uncertainties of the robot parameters, speed of the maneuver and properties of the ground. The controller is tested using two mathematical models of significantly different complexity and accuracy.
1 :  Institut des Systèmes Intelligents et Robotique (ISIR)
CNRS : UMR7222 – Université Pierre et Marie Curie [UPMC] - Paris VI
Informatique/Intelligence artificielle

Sciences de l'ingénieur/Automatique / Robotique
Liste des fichiers attachés à ce document : 
PDF
2010_IROS_Terekhov.pdf(403.1 KB)