Evolving composite robot behaviour - a modular architecture

Evolving composite robot behaviour - a modular architecture

We have developed a composite control system for solving complex tasks with autonomous robots. The control system is evolved using artificial evolution and can be regarded as a modular decision tree where every node is a neural network. We show that the control system is robust to noise, is reactive...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Larsen, T., Hansen, S.T.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Automatic control
Computational modeling
Computer science
Computer simulation
Control systems
Evolutionary computation
Neural networks
Robot control
Robot sensing systems
Robotics and automation
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We have developed a composite control system for solving complex tasks with autonomous robots. The control system is evolved using artificial evolution and can be regarded as a modular decision tree where every node is a neural network. We show that the control system is robust to noise, is reactive, is extendable and can be set up to be configured automatically. Furthermore we show that robots in the real world work using this control system.
DOI:10.1109/ROMOCO.2005.201435