Selection of optimal learning rates in CMAC based control schemes

CMAC based control schemes have been studied by many researchers. It is well recognized that properly designed CMAC controllers provide useful and practical tools for precision control of nonlinear systems. For complex trajectories, however, the convergence speed of CMAC can be slow because the CMAC module takes much time in learning the inverse dynamics of the plant. Therefore, one practical difficulty of CMAC based controller design is the selection of appropriate learning rate. In this paper, we present a method for selection of optimal CMAC learning rate. Furthermore, we demonstrate that the proposed GA-based approach to parameter selection can provide a global optimal solution. Computer simulation results confirm the effectiveness of the proposed method.