Adaptive Self-Tuning Robotic Autonomy for Unmanned Aerial Vehicles

Unmanned Aerial Vehicles have become indispensable tools across a spectrum of applications, necessitating advanced control systems capable of adapting to diverse and dynamic environments. This research addresses the G-controller performance against the traditional controlling system. In this research, a novel neurofuzzy controller model is designed, which can assist UAVs to evolve and reorganize them selves through training which can be used in various model like quadcoptors. This dynamic adaptation ensures robust performance across diverse operating conditions and minimizes the need for manual tuning or re-calibration. Key features include a generic architecture facilitating seamless integration with various UAV platforms and the ability to handle uncertainties and non-linearity inherent in real-world environments. The findings of the model was promising as the operational efficiency in trajectory and latitude tracking was optimum. Also, the model recorded best performance with metrics like flight stability, battery life and payload capacity when compared with other models.