Quadrotor Attitude Dynamics Identification Based on Nonlinear Autoregressive Neural Network with Exogenous Inputs

In the case of quadrotors, system identification is a challenging task because quadrotors are inherently unstable exhibit nonlinear behavior and significant coupling. addition to this, quadrotors’ greatly influenced by characteristics coefficients, which very hard measure directly or determine analytically. However, all difficulties listed above known be successfully overcome use artificial intelligence. this paper, two techniques were applied compared model quadrotor attitude dynamics. These Nonlinear Autoregressive Network with Exogenous Inputs (NARX) continuous-time transfer function.