Intelligent control of UAV with neuron-fuzzy approach under hierarchical architecture

As the missions to be assigned to UAV are more complex and rigorous, the need for an extended on-board intelligent control capability is crucial. The increasing power of computational resources makes possible the development of intelligent flight control systems which are capable of dealing with the complex tasks in dynamic and uncertain environments. Intelligent flight control systems make UAV have the ability to make their own decisions. Hierarchical architecture offers very convenient ways to describe the operation of complex systems and to deal with computational complexity issues, and it is used extensively in the modeling of intelligent control systems. This method combines the advantages of neural networks (ability for identification and control) with the advantages of fuzzy logic (ability for decision and use of expert knowledge) to achieve the goal of robust adaptive control of non-linear dynamic systems. This paper mainly focuses on designing intelligent control law under hierarchical architecture with neuron networks combining fuzzy control. We illustrate in this paper the new methodology with the case of controlling unmanned aircraft dynamic systems. For this case, we use Simulink models for the simulation of UAV dynamics during flight; the goal of constructing these models is to master the dynamics of the aircraft so as to have a way of controlling this dynamics to avoid dangerous behavior of UAV.