Neural Network-Based Optimal Control of a Lower-limb Exoskeleton Robot

In this paper, an optimal controller is designed and applied to the lower-limb exoskeleton robot, which could improve the robustness under nonlinear perturbations. In order to derive the optimal controller, we build the modeling of the exoskeleton robot to simplify the structure of the robot, and then we define a cost function, because the cost function is difficult to solve, so we adopt the function approximation method to approximate its optimal value, and the optimal control is obtained by solving the Hamiltonian equation. Finally, simulation studies are carried out. These simulation studies verify that the controller has a good performance even in the presence of disturbance.