Approximating an optimal feedback control law by a generalized Sugeno controller

Abstract

This paper proposes an approach to implement optimal control laws of nonlinear systems in real time. Our methodology does not require solving two-point boundary-value problems on-line and may not require it off-line either. The optimal control law is learned using a generalized Sugeno controller (GSC) from a family of optimal trajectories. We compare the trajectories generated by the GSC and the trajectories yielded by the optimal feedback control law when applied to Zermelo's ship steering problem.