Adaptive Sliding mode Control Based on RBF Neural Network Approximation for Quadrotor

This paper addresses the design of a robust adaptive sliding mode tracking control approach utilizing a Radial Basis Function Neural Network RBF NN for quadrotor. The proposed system has great advantages in dealing with nonlinearities and it has the ability to approximate uncertainties. The output of the neural network is used as a compensator parameter in order to eliminate system uncertainties. Consequently, fast error convergence in the closed loop control system can be achieved. A preliminary study to apply the system in an agricultural application using visual sensing is introduced and tested. The proposed system stability is proved by Lyapunov analysis, simulation and experimental implementation.