An integrated navigation system for a small UAV using low-cost sensors

This paper describes the flight control and navigation system of a fixed-wing unmanned aerial vehicle with low cost sensors. Furthermore, an adaptive Kalman filter algorithm with radial basic function neural network is proposed to improve attitude information performance. Based on the unmanned aerial vehicle situation information and error information, system adjusts the weights of the sensor information to get precise information. Moreover, a simple heading control algorithm is used to realize position control. The effectiveness of the proposed methods is shown by a series of simulations and experiments. The small unmanned aerial vehicle can operate in the field and send back the environment information for the control center to improve emergency management efficiency.