Recurrent CMAC Sliding Mode Adaptive Control for Flying Robot

Sliding mode adaptive control algorithm with recurrent cerebellar model articulatory controller(CMAC) was proposed for a class of uncertain nonlinear systems whose threshold value of lumped disturbance is difficult to measure in practice. The system is divided into nominal model and lumped disturbance term which is composed of modeling error, parameter uncertainties, disturbances, and unmodeled dynamics. Adaptive control is adopted to approach the uncertain input coefficient of the system, robust control is introduced to reduce the lumped disturbance to an acceptant bound within finite time, and sliding mode control is adopted to enable the tracking errors of the uncertain nonlinear system to approximate to zero ultimately. Because the threshold value of lumped disturbance is difficult to measure in practical applications, the recurrent CMAC is used as an observer to approximate it in real time. The asymptotically stability was proved based on Lyapunov stability theory, and simulation results of micro flying robot attitude control indicated that the proposed algorithm improves transient performance and robustness. Research conclusions provide the basis for effective control of complex nonlinear systems.