Discrete-Time Inverse Optimal Control for Nonlinear Systems

6  Neural Inverse Optimal Control

This chapter discusses the combination of Section 2.5, Section 3.1, Section 3.2, and Section 5.1. The results of this combination are presented in Section 6.1 to achieve stabilization and trajectory tracking for uncertain nonlinear systems, by using a RHONN scheme to model uncertain nonlinear systems, and then applying the inverse optimal control methodology. The training of the neural network is performed on-line using an extended Kalman filter. Section 6.2 establishes a block transformation for the neural model in order to solve the inverse optimal trajectory tracking as a stabilization problem for block-control form nonlinear systems. Examples illustrate the applicability of the proposed control techniques ...