Abstract
This study aims at establishing a robust intelligent control method with higher control performance and wider application region by developing the Cubic Neural Network (CNN) intelligent control method. In this study, the dynamical energy principle is embedded into the integrator of CNN that consists of multilevel parallel processing on different degree of abstraction. As a result of simulation and experiment, it was demonstrated that the integrated CNN controllers can stand up the double pendulum taking into account the cart position limit for the case of arbitrary initial condition of pendulum angle.
