Hybrid state space and echo state networks model of a miniature helicopter

To solve the problem of modeling the horizontal translational motion of a Raptor30 based miniature helicopter near hovering, a black-box model is built based on echo state networks. Combined with a state space angular motion model, a four-degree-of-freedom hybrid model is created. System identification is done using the remote control experiment data. Model validation results demonstrate that the model can predict the motion of the miniature helicopter near hovering on the whole. The model can be used to optimize parameterized controller. Closed-loop simulation further validates the model.