ISBN
Formato digital
979-13-87837-54-9
Fecha de publicación
06-10-2025
Licencia
D. R. © Copyright 2025. Alma Y. Alanis, Jorge Galvez, Omar Avalos, Eduardo Méndez-Palos, Jorge D. Rios, Adriana Peña Perez-Negron & Gabriel Martínez Soltero
Todos los contenidos de esta obra se comparten bajo la licencia Creative Commons Atri-bución/Reconocimiento-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0). Esto implica que no está autorizado el uso comercial de la obra original ni de las eventuales obras derivadas, las cuales deberán distribuirse bajo la misma licencia que rige la obra original. No obstante, se permite a terceros compartir el contenido siempre y cuando se reconozca debidamente la autoría y la publicación original en esta editorial.
J. Olín Estrada
Universidad de Guadalajara
0009-0006-2972-7539
Jorge D. Rios
Universidad de Guadalajara
0000-0001-7565-0874
Alma Yolanda Alanis García
Universidad de Guadalajara
0000-0001-9600-779X
Acerca de
Quadcopters require robust and adaptive control systems to ensure stability and trajectory tracking under dynamic environmental conditions. Traditional Proportional-Integral-Derivative (PID) controllers offer simplicity and effectiveness but lack adaptability to external disturbances such as wind gusts. This study proposes an Adaptive Neural PID controller trained using the Extended Kalman Filter (EKF) to dynamically adjust control gains in real time, enhancing trajectory tracking and disturbance rejection. The proposed approach is implemented as an outer-loop controller to regulate vehicle motion via velocity setpoints. The method is validated in a Hardware-in-the-Loop (HIL) simulation environment using a PX4-based quadcopter and Gazebo, assessing performance under nominal, moderate (6-8 m/s), and gusty wind conditions (8-14 m/s). Results demonstrate that Neural PID reduces settling time by up to 70.8% in Z-axis, improves mean squared error (MSE) by 34.2% in moderate wind, and decreases overshoot by 35.7% in lat- eral axes compared to conventional PID. Under gusty wind conditions, Neural PID provides enhanced stability in Y-axis, reducing deviations by 35.9%, though conventional PID maintains slightly lower error in X and Z. Overall, the findings highlight the effectiveness of adaptive neu- ral control for improving quadcopter resilience against environmental disturbances, making it a viable alternative for real-world applications.
Referencias
Mohsan, S.A.H., Othman, N.Q.H., Li, Y., et al.: Unmanned aerial vehicles (UAVs): practical aspects, applications, open challenges, security issues, and future trends. Intelligent Service Robotics 16, 109–137 (2023).
Gomez-Avila, J., Villaseñor, C., Hernandez-Barragan, J., Arana-Daniel, N., Ala- nis, A., Lopez-Franco, C.: Neural PD Controller for an Unmanned Aerial Vehicle Trained with Extended Kalman Filter. Algorithms, 13(2), 1–16 (2020).
Abbas, N., Abbas, Z., Zafar, D.S., Ahmed, N., Liu, X., Khan, S., Foster, E., Larkin, S.: Survey of Advanced Nonlinear Control Strategies for UAVs: Integration of Sen- sors and Hybrid Techniques. Sensors 24, 13286 (2024).
Borase, R., Maghade, D., Sondkar, S., Pawar, S.: A review of PID control, tun- ing methods and applications. International Journal of Dynamics and Control 9, (2021).
Nguyen, V.-C., Nguyen, M., Tran, H., Mien, T., La, H., Nguyen, H.: Trajectory Tracking Control for a Quadcopter under External Disturbances. Engineering, Technology & Applied Science Research 14, 17620–17628 (2024).
Derafa, L., Benallegue, A., Fridman, L.: Super twisting control algorithm for the attitude tracking of a four rotors UAV. Journal of the Franklin Institute, 349(2), 685–699 (2012).
Li, J., Wan, L., Li, J., Hou, K.: Adaptive Backstepping Control of Quadrotor UAVs with Output Constraints and Input Saturation. Applied Sciences 13, 8710 (2023).
Antonio-Toledo, M., Sanchez, E. N., Alanis, A. Y.: Neural Inverse Optimal Con- trol Applied to Quadrotor UAV. In: 2018 IEEE Latin American Conference on Computational Intelligence (LA-CCI), Guadalajara, México, pp. 1–8 (2018).
Sanchez, E., Alanis, A.: Redes Neuronales: Conceptos Fundamentales y Aplica- ciones a Control Automático. Pearson Educación, Madrid, Spain (2006).
Haykin, S.: Kalman Filtering and Neural Networks. In: Adaptive and Cognitive Dy- namic Systems: Signal Processing, Learning, Communications and Control. Wiley, Hoboken, NJ, USA (2004).
Hernandez-Barragan, J., Rios, J., Alanis, A., Lopez-Franco, C., Gomez-Avila, J., Arana-Daniel, N.: Adaptive Single Neuron Anti-Windup PID Controller Based on the Extended Kalman Filter Algorithm. Electronics, 9(4), 636 (2020).
QGroundControl Documentation. https://qgroundcontrol.com last accessed: February 21, 2025.
MAVLink Protocol. https://mavlink.io/en/ last accessed: February 21, 2025.
PX4 Autopilot Documentation. https://docs.px4.io/main/en/, last accessed: February 21, 2025.
MAVLink Protocol: Common Message Set. https://mavlink.io/en/messages/ common.html, last accessed: February 21, 2025.
Rao, J., Li, B., Zhang, Z., Chen, D., Giernacki, W.: Position Control of Quadrotor UAV Based on Cascade Fuzzy Neural Network. Energies 15(5), 1763 (2022).
Karimoddini, A., Lin, H., Chen, B., Lee, T.: Hierarchical hybrid modelling and control of an unmanned helicopter. International Journal of Control 87, 10–1080 (2014).
Cai, G., Chen, B.M., Lee, T.H.: Coordinate Systems and Transformations. In:
Unmanned Rotorcraft Systems, pp. 23–34. Springer, London (2011).
Reyes Cortés, F., Cid Monjaraz, J.: Drones: Cinemática, Dinámica y Control de Cuadricópteros. Alfaomega Grupo Editor, Ciudad de México (2019).
National Weather Service (NOAA): Official Website. https://www.weather.gov, last accessed: February 21, 2025.
Royal Meteorological Society: Beaufort Wind Scale. https://www.rmets.org/ metmatters/beaufort-wind-scale, last accessed: February 21, 2025