A Robust Adaptive RBFNN Augmenting Backstepping Control Approach for a Model-Scaled Helicopter

摘要

This brief investigates the trajectory tracking problem for a model-scaled helicopter with a novel robust adaptive radial basis function neural network (RBFNN) augmenting backstepping control approach. The helicopter model is first decomposed into an approximate strict-feedback format with some unmodeled dynamics. Backstepping technique is employed as the main control framework, which is augmented by robust RBFNNs to approximate the unmodeled dynamics. Each robust RBFNN utilizes an th-order smooth switching function to combine a conventional RBFNN with a robust control. The conventional RBFNN dominates in the neural active region, while the robust control retrieves the transient outside the active region, so that the stability range can be widened. In addition, command filters are employed to approximate derivatives of the virtual controls in the backstepping procedure. This systematic design methodology is proven to achieve ultimate boundedness of the closed-loop helicopter system. Simulations validate the effectiveness of the proposed control approach.