Hybrid LQG-Neural Controller for Inverted Pendulum System

Simple item page
dc.creatorSazonov, E. S.
dc.creatorKlinkhachorn, P.
dc.creatorKlein, R. L.
dc.date2003-11-30
dc.date.accessioned2026-07-07T03:20:40Z
dc.date.available2026-07-07T03:20:40Z
dc.descriptionThe paper presents a hybrid system controller, incorporating a neural and an LQG controller. The neural controller has been optimized by genetic algorithms directly on the inverted pendulum system. The failure free optimization process stipulated a relatively small region of the asymptotic stability of the neural controller, which is concentrated around the regulation point. The presented hybrid controller combines benefits of a genetically optimized neural controller and an LQG controller in a single system controller. High quality of the regulation process is achieved through utilization of the neural controller, while stability of the system during transient processes and a wide range of operation are assured through application of the LQG controller. The hybrid controller has been validated by applying it to a simulation model of an inherently unstable system of inverted pendulum.
dc.identifierhttps://arxiv.org/abs/cs/0312003
dc.identifierhttp://arxiv.org/abs/cs/0312003
dc.identifierProceedings of 35th Southeastern Symposium on System Theory (SSST), Morgantown, WV, March 2003
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/31907
dc.subjectNeural and Evolutionary Computing
dc.subjectMachine Learning
dc.subjectI.2.6;C.1.3;I.5.1
dc.titleHybrid LQG-Neural Controller for Inverted Pendulum System
dc.typetext

Files

Collections

arXiv