Extracting FSA descriptions of robot behaviours from the dynamics of automatically designed controller networks

Matteini, Michele (2015) Extracting FSA descriptions of robot behaviours from the dynamics of automatically designed controller networks. [Laurea magistrale], Università di Bologna, Corso di Studio in Ingegneria e scienze informatiche [LM-DM270] - Cesena
Documenti full-text disponibili:
[img]
Anteprima
Documento PDF
Download (2MB) | Anteprima

Abstract

Automatic design has become a common approach to evolve complex networks, such as artificial neural networks (ANNs) and random boolean networks (RBNs), and many evolutionary setups have been discussed to increase the efficiency of this process. However networks evolved in this way have few limitations that should not be overlooked. One of these limitations is the black-box problem that refers to the impossibility to analyze internal behaviour of complex networks in an efficient and meaningful way. The aim of this study is to develop a methodology that make it possible to extract finite-state automata (FSAs) descriptions of robot behaviours from the dynamics of automatically designed complex controller networks. These FSAs unlike complex networks from which they're extracted are both readable and editable thus making the resulting designs much more valuable.

Abstract
Tipologia del documento
Tesi di laurea (Laurea magistrale)
Autore della tesi
Matteini, Michele
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Ordinamento Cds
DM270
Parole chiave
Boolean Network Automatic Design Trajectories Robot Behaviour
Data di discussione della Tesi
19 Marzo 2015
URI

Altri metadati

Statistica sui download

Gestione del documento: Visualizza il documento

^