PROJECT TITLE :
This paper presents a discrete-time inverse optimal neural controller, which is constituted by combination of two techniques: 1) inverse optimal management to avoid solving the Hamilton–Jacobi–Bellman equation related to nonlinear system optimal control and a pair of) on-line neural identification, employing a recurrent neural network trained with an extended Kalman filter, so as to create a model of the assumed unknown nonlinear system. The inverse optimal controller relies on passivity theory. The applicability of the proposed approach is illustrated via simulations for an unstable nonlinear system and a planar robot.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here