Learning strategy for optimal fuzzy control

In this paper, a new scheme of fuzzy optimal control for discrete-time nonlinear systems based on the Pontryagin’s Minimum Principle is proposed. Using back propagation from the final co-state error and gradient descent, a method which allows training an adaptive fuzzy inference system to estimate values for the co-state variables converging to the optimal ones is devised. This approach allows finding a solution to the optimal control problem on-line by training the system, rather than by pre-computing it. Finally, this optimal approach is applied to nonlinear control benchmark problems. The results demonstrate the effectiveness of the approach towards achieving the optimal control objective.This work was supported by the Portuguese "Fundação para a Ciência e a Tecnologia (FCT)" under grant POSI/SRI/41975/2001