Coevolutionary design of a control system for nonlinear uncertain plants

The paper proposes and analyzes an alternative for autonomously developing control systems for nonlinear, uncertain plants. The proposed alternative uses a neural-like controller with a special architecture and also a specific developing algorithm. The developing algorithm estimates the parameters and the structure of the controller during an off-line training stage. The controller obtained at the end of the off-line training is for the on-line use, no longer requiring an extra-training. The developing algorithm is implemented like a multi-agent system so that the agents cooperate one another. For each agent the developing algorithm implements a local evolution and a temporal evolution. For the partition where the agent works, the local evolution estimates, through a coevolutionary algorithm, the best "segment" of the control function for the worst possible plant. We present two different implementations of the developing algorithm. The first implementation, based on global cooperation between agents, is performed through changing controllers structures between agents. The second implementation, based on local cooperation between agents, is performed through changing individual wavelets between agents.