Robust Motion Control for Aerial Robotic Systems in Monitoring Applications

Mobile robots usage have allowed a properly performance of complex tasks in various fields without human intervention. Unmanned aerial robots have been successfully used in monitoring applications within indoor and outdoor scenarios. The main contribution of this research is to introduce a novel robust neural sliding-mode control for a four-rotor aerial robot in monitoring tasks. To verify the effectiveness of the proposed motion control scheme, it is considered a simulation scenario where the vehicle is subjected to unknown disturbances while the robot is flying towards different operation points, as required in real-time monitoring applications. Bézier polynomials are suitably integrated in the motion control scheme to smooth the system motion. Additional case study is also included where B-spline artificial neural networks are efficiently introduced for improving the system performance while maintaining its stability despite random undesired abrupt position changes due to the induced forces by wind. Finally, to highlight the effectiveness of the introduced controller, the vehicle is simulated in a virtual scenario where a rapidly exploring random tree (RRT) algorithm is implemented for determining the best path in a constrained space. This preliminary results effectively promote the development of cyber-physical systems for monitoring application management, as required in the electric power systems.