No abstract

In recent years, multi-rotor UAVs have become valuable tools in several productive fields, from entertainment to agriculture and security. However, during their flight trajectory, they sometimes do not accurately perform a specific set of tasks, and the implementation of flight controllers in these vehicles is required to achieve a successful performance. Therefore, this research describes the design of a flight position controller based on Deep Neural Networks and subsequent implementation for a multi-rotor UAV. Five promising Neural Network architectures are developed based on a thorough literature review, incorporating LSTM, 1-D convolutional, pooling, and fully-connected layers. A dataset is then constructed using the performance data of a PID flight controller, encompassing diverse trajectories with transient and steady-state information such as position, speed, acceleration, and motor output signals. The tuning of hyperparameters for each type of architecture is performed by applying the Hyperband algorithm. The best model obtained (LSTMCNN) consists of a combination of LSTM and CNN layers in one dimension. This architecture is compared with the PID flight controller in different scenarios employing evaluation metrics such as rise time, overshoot, steady-state error, and control effort. The findings reveal that our best models demonstrate the successful generalization of flight control tasks. While our best model is able to work with a wider operational range than the PID controller and offers step responses in the Y and X axis with 97% and 98% similarity, respectively, within the PID’s operational range. This outcome opens up possibilities for efficient online training of flight controllers based on Neural Networks, enabling the development of adaptable controllers tailored to specific application domains.