Research Article
BibTex RIS Cite

Intelligent Quadcopter Control Using Artificial Neural Networks

Year 2023, , 138 - 142, 01.03.2023
https://doi.org/10.35414/akufemubid.1229424

Abstract

An advanced controller architecture and design for quadcopter control implementation is proposed in this study. Instead of using only the error information as input to the controller, reference and measured outputs are used separately independent from each other. This enhances the performance of the controller of quadcopter being a highly non-linear platform. In this study single layer neural network is directly used as a controller. A complex controller is grown from an initially simple PID controller. This elevates the need for time consuming search in huge parameter space due to very high dimensions. About ten percent improvement over state-of-the-art controllers is observed and results are reported both numerically and graphically. Promising results encourage to use the type of controller proposed for various real applications.

References

  • Agarwal, V., & Tewari, R. R., 2021. Improving energy efficiency in UAV attitude control using deep reinforcement learning. Journal of Scientific Research, 65(3), 209-219.
  • Barzegar, A., & Lee, D. J., 2022. Deep Reinforcement Learning-Based Adaptive Controller for Trajectory Tracking and Altitude Control of an Aerial Robot. Applied Sciences, 12(9), 4764.
  • Bouadi, H., Cunha, S. S., Drouin, A., & Mora-Camino, F., 2011, November. Adaptive sliding mode control for quadrotor attitude stabilization and altitude tracking. In 2011 IEEE 12th international symposium on computational intelligence and informatics (CINTI) (pp. 449-455). IEEE.
  • El Gmili, N., Mjahed, M., Elkari, A., & Ayad, H., 2022. Improved cuckoo search approach based optimal proportional-derivative parameters for quadcopter flight control. Australian Journal of Electrical and Electronics Engineering, 1-14.
  • Idrissi, M., Salami, M., & Annaz, F., 2022. A Review of Quadrotor Unmanned Aerial Vehicles: Applications, Architectural Design and Control Algorithms. Journal of Intelligent & Robotic Systems, 104(2), 1-33.
  • Jin, X. Z., He, T., Wu, X. M., Wang, H., & Chi, J., 2020. Robust adaptive neural network-based compensation control of a class of quadrotor aircrafts. Journal of the Franklin Institute, 357(17), 12241-12263.
  • Karakaya, Ş. E., & Goren, A., 2022. Performance Comparison of PID and NARX Neural Network for Attitude Control of a Quadcopter UAV. Journal of Materials and Mechatronics: A, 3(1), 1-19.
  • Park, D., Yu, H., Xuan-Mung, N., Lee, J., & Hong, S. K. (2019, December). Multicopter PID Attitude Controller Gain Auto-tuning through Reinforcement Learning Neural Networks. In Proceedings of the 2019 2nd International Conference on Control and Robot Technology (pp. 80-84).
  • Sonugur, G., Gokce, C. O., Koca, Y. B., Inci, S. S., & Keles, Z., 2021, January. Particle swarm optimization based optimal PID controller for quadcopters. In Dokl Bulg Akad Nauk (Vol. 74, No. 12, pp. 1806-14).
  • Suhail, S. A., Bazaz, M. A., & Hussain, S., 2022. Adaptive sliding mode-based active disturbance rejection control for a quadcopter. Transactions of the Institute of Measurement and Control, 01423312221099366.
  • Yoon, J., & Doh, J., 2022. Optimal PID control for hovering stabilization of quadcopter using long short term memory. Advanced Engineering Informatics, 53, 101679.

Yapay Sinir Ağları Kullanarak Akıllı Kuadkopter Kontrolü

Year 2023, , 138 - 142, 01.03.2023
https://doi.org/10.35414/akufemubid.1229424

Abstract

Bu çalışmada ileri seviyede bir kontrolör mimarisi tasarlanmış ve geliştirilmiştir. Kontrolöre girdi olarak sadece hata sinyali yerine referans ve ölçüm sinyalleri ayrı ayrı girilmiştir. Bu yaklaşım doğrusallıktan yüksek derecede farklı olan kuadkopterin kontrol performansını artırmıştır. Bu çalışmada tek katmanlı sinir ağı doğrudan kontrolör olarak kullanılmıştır. Basitten başlayarak daha karmaşık bir kontrolörü tasarlayarak bir bakıma kontrolör büyütme yapılmıştır. Bu sayede son derece yüksek boyutlu olan parametre uzayında arama zamanı oldukça azaltılmıştır. Literatürdeki mevcut başarılı kontrolörlere göre yüzde on civarında bir performans artışı gözlemlenmiştir. Sonuçlar hem numerik olarak hem de grafiksel olarak verilmiştir. Elde edilen cesaret verici sonuçlar önerilen kontrolör algoritmasının yeni platformlarda da denenmesinin yolunu açacaktır.

References

  • Agarwal, V., & Tewari, R. R., 2021. Improving energy efficiency in UAV attitude control using deep reinforcement learning. Journal of Scientific Research, 65(3), 209-219.
  • Barzegar, A., & Lee, D. J., 2022. Deep Reinforcement Learning-Based Adaptive Controller for Trajectory Tracking and Altitude Control of an Aerial Robot. Applied Sciences, 12(9), 4764.
  • Bouadi, H., Cunha, S. S., Drouin, A., & Mora-Camino, F., 2011, November. Adaptive sliding mode control for quadrotor attitude stabilization and altitude tracking. In 2011 IEEE 12th international symposium on computational intelligence and informatics (CINTI) (pp. 449-455). IEEE.
  • El Gmili, N., Mjahed, M., Elkari, A., & Ayad, H., 2022. Improved cuckoo search approach based optimal proportional-derivative parameters for quadcopter flight control. Australian Journal of Electrical and Electronics Engineering, 1-14.
  • Idrissi, M., Salami, M., & Annaz, F., 2022. A Review of Quadrotor Unmanned Aerial Vehicles: Applications, Architectural Design and Control Algorithms. Journal of Intelligent & Robotic Systems, 104(2), 1-33.
  • Jin, X. Z., He, T., Wu, X. M., Wang, H., & Chi, J., 2020. Robust adaptive neural network-based compensation control of a class of quadrotor aircrafts. Journal of the Franklin Institute, 357(17), 12241-12263.
  • Karakaya, Ş. E., & Goren, A., 2022. Performance Comparison of PID and NARX Neural Network for Attitude Control of a Quadcopter UAV. Journal of Materials and Mechatronics: A, 3(1), 1-19.
  • Park, D., Yu, H., Xuan-Mung, N., Lee, J., & Hong, S. K. (2019, December). Multicopter PID Attitude Controller Gain Auto-tuning through Reinforcement Learning Neural Networks. In Proceedings of the 2019 2nd International Conference on Control and Robot Technology (pp. 80-84).
  • Sonugur, G., Gokce, C. O., Koca, Y. B., Inci, S. S., & Keles, Z., 2021, January. Particle swarm optimization based optimal PID controller for quadcopters. In Dokl Bulg Akad Nauk (Vol. 74, No. 12, pp. 1806-14).
  • Suhail, S. A., Bazaz, M. A., & Hussain, S., 2022. Adaptive sliding mode-based active disturbance rejection control for a quadcopter. Transactions of the Institute of Measurement and Control, 01423312221099366.
  • Yoon, J., & Doh, J., 2022. Optimal PID control for hovering stabilization of quadcopter using long short term memory. Advanced Engineering Informatics, 53, 101679.
There are 11 citations in total.

Details

Primary Language English
Subjects Electrical Engineering
Journal Section Articles
Authors

Celal Onur Gökçe 0000-0003-3120-7808

Publication Date March 1, 2023
Submission Date January 4, 2023
Published in Issue Year 2023

Cite

APA Gökçe, C. O. (2023). Intelligent Quadcopter Control Using Artificial Neural Networks. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, 23(1), 138-142. https://doi.org/10.35414/akufemubid.1229424
AMA Gökçe CO. Intelligent Quadcopter Control Using Artificial Neural Networks. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi. March 2023;23(1):138-142. doi:10.35414/akufemubid.1229424
Chicago Gökçe, Celal Onur. “Intelligent Quadcopter Control Using Artificial Neural Networks”. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi 23, no. 1 (March 2023): 138-42. https://doi.org/10.35414/akufemubid.1229424.
EndNote Gökçe CO (March 1, 2023) Intelligent Quadcopter Control Using Artificial Neural Networks. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi 23 1 138–142.
IEEE C. O. Gökçe, “Intelligent Quadcopter Control Using Artificial Neural Networks”, Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, vol. 23, no. 1, pp. 138–142, 2023, doi: 10.35414/akufemubid.1229424.
ISNAD Gökçe, Celal Onur. “Intelligent Quadcopter Control Using Artificial Neural Networks”. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi 23/1 (March 2023), 138-142. https://doi.org/10.35414/akufemubid.1229424.
JAMA Gökçe CO. Intelligent Quadcopter Control Using Artificial Neural Networks. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi. 2023;23:138–142.
MLA Gökçe, Celal Onur. “Intelligent Quadcopter Control Using Artificial Neural Networks”. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, vol. 23, no. 1, 2023, pp. 138-42, doi:10.35414/akufemubid.1229424.
Vancouver Gökçe CO. Intelligent Quadcopter Control Using Artificial Neural Networks. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi. 2023;23(1):138-42.


Bu eser Creative Commons Atıf-GayriTicari 4.0 Uluslararası Lisansı ile lisanslanmıştır.