Intelligent coordination of multiple systems with neural networks

A multiple-system coordinator that combines the techniques of intelligent control and neural networks, and forms the high-level coordinator in a hierarchical structure, is proposed. The basic idea is to estimate the effects of the control commands to subsystems using a predictor and modify these commands using a knowledge-based coordinator so as to achieve the desired performance. The predictor was designed for multiple-input, multiple-output systems using neural networks. The knowledge-based coordinator is responsible for a goal-oriented search in its knowledge base and the overall system stability. As an example, the coordination of two two-link robots holding a single object is discussed