Show simple item record

dc.contributor.authorFidan, B.en_US
dc.contributor.authorSezer, Erolen_US
dc.contributor.authorAkar, M.en_US
dc.coverage.spatialDenver, CO, USA
dc.date.accessioned2016-02-08T11:55:30Z
dc.date.available2016-02-08T11:55:30Z
dc.date.issued2003-06en_US
dc.identifier.urihttp://hdl.handle.net/11693/27516
dc.descriptionDate of Conference: 4-6 June 2003
dc.descriptionConference name: Proceedings of the 2003 American Control Conference
dc.description.abstractAn efficient approach to nonlinear control problems in which the plant is to be driven to a desired state using a neural network controller in a number of steps is by representing the whole process as a multi - stage neural network. In this paper, an explicit formulation of the back propagation algorithm is developed for such networks. Later, this approach is used to build up a path planner for a mechanical snake (a robot composed of a sequence of articulated links). This path planner, together with a tracking algorithm, is shown to get the mechanical snake out of a collision-free closed region.en_US
dc.language.isoEnglishen_US
dc.source.titleProceedings of the American Control Conference, 2003en_US
dc.relation.isversionofhttps://doi.org/10.1109/ACC.2003.1239764
dc.subjectAlgorithmsen_US
dc.subjectBackpropagationen_US
dc.subjectMotion planningen_US
dc.subjectNeural networksen_US
dc.subjectMechanical snakeen_US
dc.subjectNonlinear control systemsen_US
dc.titleMulti-stage neural networks with application to motion planning of a mechanical snakeen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.citation.spage1278en_US
dc.citation.epage1283en_US
dc.identifier.doi10.1109/ACC.2003.1239764
dc.publisherIEEE


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record