Search

This paper investigates the development of a deep learning-based flight control model for a tilt-rotor unmanned aerial vehicle, focusing on altitude, speed, and roll hold systems. Training data is gathered from the X-Plane flight simulator, employing a proportional–integral–derivative controller to enhance flight dynamics and data quality. The model architecture, implemented within the TensorFlow framework, undergoes iterative tuning for optimal performance. Testing involved two scenarios: wind-free conditions and wind disturbances. In wind-free conditions, the model demonstrated excellent tracking performance, closely tracking the desired altitude. The model's robustness is further evaluated by introducing wind disturbances. Interestingly, these disturbances do not significantly impact the model performance. This research has demonstrated data-driven flight control in a tilt-rotor unmanned aerial vehicle, offering improved adaptability and robustness compared to traditional methods. Future work may explore further flight modes, environmental complexities, and the utilization of real test flight data to enhance the model generalizability. [ABSTRACT FROM AUTHOR]