Neuro-fuzzy controller for helicopter motion control

This paper presents a neuro-fuzzy controller to control a nonlinear system such as the flight of a helicopter in the hover and forward flight mode positions. Hovering is a formidable stability problem, where helicopter pilots typically train for weeks before managing to do it manually. Hence automating this operation is in itself an impressive achievement. In this work, the neuro-fuzzy controller is based on the union of a fuzzy logic controller (FLC) and a general regression neural network (GRNN) for each control input of the helicopter. In the FLC's, the fuzzy inference used it is the Takagi and Sugeno type where the main difference to the other fuzzy inference types come from the specification of the consequent part. The GRNN provides estimates of continuous variables and is a one-pass learning algorithm with a highly parallel structure. Even with sparse data in a multidimensional measurement space, the algorithm provides smooth transitions from one observed value to another. It was implemented a clustering algorithm to reduce the computation amount to obtain an estimate due to a large data gathered for training. The performance of the neuro-fuzzy controller is verified with simulation results.