Self-Learning in Aerial Robotics Using Type-2 Fuzzy Systems: Case Study in Hovering Quadrotor Flight Control

This paper aims to design an enhanced self-adaptive interval type-2 fuzzy control system (ESAF2C) for stabilization of a quadcopter drone under external disturbances. Due to the ability to accommodate the footprint-of-uncertainty (FoU), an interval type-2 Takagi-Sugeno fuzzy scheme is employed to directly address the uncertainties in the nonlinear system. Sliding mode control (SMC) is utilized to optimize the upper and lower parameters of our proposed ESAF2C system using a self-tuning technique. The `Enhanced Iterative Algorithm with Stop Condition' type-reducer is accommodated in the proposed design for its suitability to real-time implementation. To handle external disturbances and the ground effect in the closed-loop flight control system, a robustness term is added to the control effort. Lyapunov theory is applied to prove the stability of our closed loop control system. Moreover, we study the measurement noise effect for different levels of noise powers using our proposed technique. The efficacy of the proposed controller is investigated in a hovering quadcopter drone through numerical simulations and real-time flight tests in the presence of external disturbances. We highlight the disturbance rejection capability of our proposed control system with respect to type-1 fuzzy and conventional PID controllers.