Dynamic Neural Network-Based Sliding Mode Estimation of Quadrotor Systems

A dynamic neural network (DNN)-based observer design is presented, which amalgamates an adaptive neural network-based technique with a sliding mode estimation method. The proposed observer design is motivated by practical quadrotor tracking control applications, where direct sensor measurements of translational and rotational rates are not available for feedback. While sliding mode estimation strategies are well established as an effective means to compensate for bounded disturbances and dynamic model uncertainty, the proposed observer design employs a feedforward adaptive DNN-based estimation term in addition to a robust, high-gain feedback sliding mode element. The use of the DNN-based term in the estimator design is motivated by the desire to improve transient performance and reduce steady state error. The DNN-based feedforward term could also offer the advantage of reducing the control effort that would be required when the proposed observer design is operating as part of a closed-loop control system. A Lyapuov-based stability analysis is utilized to prove that the proposed DNN-based observer achieves asymptotic estimation of the quadrotor altitude and attitude rates in the presence of model uncertainty and bounded disturbances (e.g., sensor noise). Numerical simulation results are also provided to demonstrate the improved performance that is achieved by incorporating the adaptive DNN in the observer.