Computational intelligence for UAV autonomous navigation with multisensor data fusion

Application and development of Unmanned Aerial Vehicles (UAVs) have rapidly growth. The flight control of these aircrafts can be performed remotely or autonomously. The UAV positioning can be done using embedded sensors, Global Satellite Navigation Systems (GNSS) signal, or both strategies. The use of the GNSS signals may have some difficulties in the presence of natural or human interference. Therefore, an alternative system is necessary to ensure a safety navigation. One solution is to use multisensor data fusion for autonomous navigation. Two approaches to multisensor data fusion are investigated. A first one is based on an adaptive neuro-fuzzy inference system, and the second approach a multilayer perceptron neural network is applied. The obtained results are promising for both approaches, especially regarding real-time processing applications.