ITEM VIEW

Computer-controlled human body coordination

dc.contributor.advisorVan Zijl, L.
dc.contributor.authorHakl, Henry
dc.contributor.otherStellenbosch University. Faculty of Science. Dept. of Mathematical Sciences.en_ZA
dc.date.accessioned2012-08-27T11:33:04Z
dc.date.available2012-08-27T11:33:04Z
dc.date.issued2003-12
dc.identifier.urihttp://hdl.handle.net/10019.1/49756
dc.descriptionThesis (MSc) -- University of Stellenbosch, 2003.en_ZA
dc.description.abstractENGLISH ABSTRACT: A need for intelligent robotic machines is identified. Research and experiments have focussed on stable, or relatively stable, dynamic simulated systems to demonstrate the feasibility of embedding advanced AI into dynamic physical systems. This thesis presents an attempt to scale the techniques to a dynamically highly unstable system - the coordination of movements in a humanoid model. Environmental simulation, articulated systems and artificial intelligence methods are identified as three essential layers for a complete and unified approach to embedding AI into robotic machinery. The history of the physics subsystem for this project is discussed, leading to the adoption of the Open Dynamics Engine as the physics simulator of choice. An approach to articulated systems is presented along with the EBNF of a hierarchical articulated system that was used to describe the model. A revised form of evolution is presented and justified. An AI model that makes use of this new evolutionary paradigm is introduced. A variety of AI variants are defined and simulated. The results of these simulations are presented and analysed. Based on these results recommendations for future work are made.en_ZA
dc.description.abstractAFRIKAANSE OPSOMMING: Die beheer van dinamiese masjiene, soos intelligente robotte, is tans beperk tot fisies stabilie - of relatief stabiele - sisteme. In hierdie tesis word die tegnieke van kunsmatige intelligensie (KI) toegepas op die kontrole en beheer van 'n dinamies hoogs onstabiele sisteem: 'n Humanoïede model. Fisiese simulasie, geartikuleerde sisteme en kunmatige intelligensie metodes word geïdentifiseer as drie noodsaaklike vereistes vir 'n volledige en eenvormige benadering tot KI beheer in robotte. Die implementasie van 'n fisiese simulator word beskryf, en 'n motivering vir die gebruik van die sogenaamde "Open Dynamics Engine" as fisiese simulator word gegee. 'n Benadering tot geartikuleerde sisteme word beskryf, tesame met die EBNF van 'n hierargiese geartikuleerde sisteem wat gebruik is om die model te beskryf. 'n Nuwe interpretasie vir evolusie word voorgestel, wat die basis vorm van 'n KI model wat in die tesis gebruik word. 'n Verskeidenheid van KI variasies word gedefineer en gesimuleer, en die resultate word beskryf en ontleed. Voorstelle vir verdere navorsing word gemaak.af_ZA
dc.format.extent97 p. : ill.
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.subjectRoboticsen_ZA
dc.subjectArtificial intelligenceen_ZA
dc.subjectHuman mechanics -- Computer simulationen_ZA
dc.subjectEmbedded computer systemsen_ZA
dc.subjectDissertations -- Computer scienceen_ZA
dc.titleComputer-controlled human body coordinationen_ZA
dc.typeThesisen_ZA
dc.rights.holderStellenbosch Universityen_ZA


Files in this item

Thumbnail

This item appears in the following Collection(s)

ITEM VIEW