Title :
Fuzzy reinforcement learning control for compliance tasks of robotic manipulators
Author :
Tzafestas, S.G. ; Rigatos, G.G.
Author_Institution :
Dept. of Electr. & Comput. Eng., Nat. Tech. Univ. of Athens, Greece
fDate :
2/1/2002 12:00:00 AM
Abstract :
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
Keywords :
compliance control; fuzzy control; fuzzy logic; intelligent control; learning (artificial intelligence); manipulators; variable structure systems; FRL scheme; compliance tasks; fuzzy logic; fuzzy reinforcement learning; fuzzy reinforcement learning control; hybrid hierarchical control; immediate reward; impedance control; metal surface deburring; optimal task performance; robotic manipulators; sliding-mode control; sufficient conditions; Control systems; Convergence; Deburring; Fuzzy control; Fuzzy logic; Iterative algorithms; Learning; Manipulators; Service robots; Sliding mode control;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/3477.979965
