Hybrid Control of a Robotic Manipulator by the Neural Network Model (6th Report, Hierarchical Intelligent Control System)

In this paper, we present a new scheme for intelligent control of robotic manipulators. This scheme is an integrated approach of the Neuromorphic and Symbolic control, including the applied neural network for the servo control and the knowledge-based approximation. The neural network in the servo level is the numerical manipulation, while the knowledge-based part is the symbolic manipulation. In Neuromorphic control, the neural network compensates the nonlinearity of the system and the uncertainty in environment. The knowledge-base part forms symbolic control strategy for the servo level. This is control system analogous to the human cerebral control structure.