Fuzzy reinforcement learning control for compliance tasks of robotic manipulators

Fuzzy reinforcement learning control for compliance tasks of robotic manipulators

A fuzzy reinforcement learning (FRL) scheme which is based on the principles of sliding-mode control and fuzzy logic is proposed. The FRL uses only immediate reward. Sufficient conditions for the convergence of the FRL to the optimal task performance are studied. The validity of the method is tested...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on cybernetics 2002-02, Vol.32 (1), p.107-113
Hauptverfasser: Tzafestas, S.G., Rigatos, G.G.
Format: Artikel
Sprache:eng
Schlagworte:
Control systems
Convergence
Cybernetics
Deburring
Fuzzy
Fuzzy control
Fuzzy logic
Fuzzy set theory
Iterative algorithms
Learning
Manipulators
Reinforcement
Robots
Service robots
Sliding mode control
Tasks
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A fuzzy reinforcement learning (FRL) scheme which is based on the principles of sliding-mode control and fuzzy logic is proposed. The FRL uses only immediate reward. Sufficient conditions for the convergence of the FRL to the optimal task performance are studied. The validity of the method is tested through simulation examples of a robot which deburrs a metal surface.
ISSN:1083-4419
2168-2267
1941-0492
2168-2275
DOI:10.1109/3477.979965