Modeling and control of unmanned aerial vehicle using self-organizing map multiple models

This paper use self organizing map neural work based multiple models method in modeling and controller designing for the maneuver of unmanned aerial vehicle. The self organizing map neural network is used to partition the working space of vehicle and a linear model is built in every subspace to approximate the nonlinear kinetics of vehicle in local subspace. The controller is also designed based on the linear model. A switched-adaptive multiple models control scheme based on self organizing map neural network is proposed for the maneuver of unmanned aerial vehicle. Besides the response speed, the method also improves the control precision of unmanned aerial vehicle. The simulation presents the performance of modeling and controller designing based on this method.