Trajectory Tracking Control of Autonomous Quadrotor Helicopter Using Robust Neural Adaptive Backstepping Approach

AbstractThis paper presents the design and analysis of a robust neural adaptive backstepping control (RNABC) for an autonomous quadrotor helicopter perturbed by time-varying external disturbances. The work uses a backstepping method and a radial basis function neural network (RBFNN), which estimates perturbation. A gravitational search algorithm (GSA) is included to optimize the backstepping controller for a nominal dynamic model of a helicopter. Disturbances caused by external sources are estimated using the global estimation attribute of the RBFNN. To further improve the control design performance, a robust compensator is introduced to eliminate the approximation error produced by the neural approximator. Asymptotical stability of the closed loop control system is analytically proven via the Lyapunov theorem. The main advantage of the proposed methodology is that it requires no advance knowledge of the disturbances. A quadrotor helicopter is simulated to track trajectories. The effectiveness of the controller is also validated by realistic effects such as model uncertainty and measurement noise. The results show the efficiency and usefulness of the designed approach.