论文信息 - 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 through simulation examples of a robot which deburrs a metal surface.

Spyros G. Tzafestas | Gerasimos G. Rigatos | S. Tzafestas | G. Rigatos

[1] Andrew W. Moore,et al. Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[2] V. Utkin. Variable structure systems with sliding modes , 1977 .

[3] Kuu-young Young,et al. Reinforcement Learning and Robust Control for Robot Compliance Tasks , 1998, J. Intell. Robotic Syst..

[4] Luca Maria Gambardella,et al. On the iterative learning control theory for robotic manipulators , 1988, IEEE J. Robotics Autom..

[5] Dr. Rainer Palm,et al. Model Based Fuzzy Control , 1997, Springer Berlin Heidelberg.

[6] Spyros G. Tzafestas,et al. Reactive parking control of nonholonomic vehicles via a fuzzy learning automaton , 2001 .

[7] Weiping Li,et al. Applied Nonlinear Control , 1991 .

[8] V. Gullapalli,et al. Acquiring robot skills via reinforcement learning , 1994, IEEE Control Systems.

[9] Dimitri P. Bertsekas,et al. Dynamic Programming and Optimal Control, Two Volume Set , 1995 .