Helicopter tracking control using direct neural dynamic programming

This paper advances a newly introduced neural learning control mechanism for helicopter flight control design. Based on direct neural dynamic programming (DNDP), the control system is tailored to learn to maneuver a helicopter in addition to its trimming and stabilization capabilities presented in earlier works. The paper consists of a comprehensive treatise of DNDP and extensive simulation studies of DNDP designs for controlling an Apache helicopter. Design robustness is addressed by performing simulations under various disturbance conditions. All the designs are tested using FLYRT, a sophisticated industry-scale nonlinear validated model of the Apache helicopter. Though illustrated for helicopters, our DNDP control system framework should be applicable for general purpose tracking control