The presence of disturbances during flight may destabilize the quadrotor control and could compromise the designated mission. This paper proposes an improved quadrotor flight control in the presence of wind disturbances where the performance will be more robust in many flight conditions. This is achieved by integrating artificial intelligence (AI) technique with disturbance observer-based feedback linearization to improve the disturbance approximation and compensation. The AI technique via radial basis function neural network (RBFNN) is implemented to compensate the bounded estimation error produced by the disturbance observer. The weights of the neural network are tuned online with no prior training required. Simulation results demonstrate the effectiveness and feasibility of the proposed technique. Keywords: Disturbance observer, feedback linearization, neural network, quadcopter

Tower crane is one of the flexible maneuvering systems that has been applied pervasively as a powerful big-scale construction machine. The under-actuated tower crane system has nonlinearity behavior with a coupling between translational and slew motions which increases the crane control challenge. In practical applications, most of the tower cranes are operated by a human operator which lead to unsatisfactory control tasks. Motivated to overcome the issues, this paper proposes a fuzzy logic controller based on single input rule modules dynamically connected fuzzy inference system for slew/translational positioning and swing suppressions of a 3 degree-of-freedom tower crane system. The proposed method can reduce the number of rules significantly, resulting in a simpler controller design. The proposed method achieves higher suppressions of at least 56% and 81% in the overall in-plane and out-plane swing responses, respectively as compared to PSO based PID+PD control.