Abstract
This paper presents a new and practical neural network-based optimal control method for a quadrotor system. Due to the difficulty in obtaining the exact model of the quadrotor system and also to deal with its nonlinear characteristic in both simulation and practice, choosing an effective intelligent controller possessing less complexity can increase system stability. For this purpose, the kinematic relations and the 6–DOF dynamic model of the quadrotor are first extracted. Subsequently, a neural network control method is proposed as the main controller to overcome the system nonlinearities as well as the corresponding unstable dynamics. Accordingly, an enumerative learning method is used to optimize the neural network’s weights. At last, the performance of the proposed control method is evaluated and then compared to a PID control method using simulation and experiment. The outcomes of this paper clearly reveal that the optimal neural network controller has a good performance in achieving minimum error.
Similar content being viewed by others
Abbreviations
- \(X\) :
-
Linear position along xe-axis with (m)
- \(Y\) :
-
Linear position along ye-axis (m)
- \(Z\) :
-
Linear position along ze-axis (m)
- \(U\) :
-
Linear velocity along xe-axis (m/s)
- \(V\) :
-
Linear velocity along ye-axis (m/s)
- \(W\) :
-
Linear velocity along ze-axis (m/s)
- \(P\) :
-
Angular velocity along xe-axis (rad/s)
- \(Q\) :
-
Angular velocity along ye-axis (rad/s)
- \(R\) :
-
Angular velocity along ze-axis (rad/s)
- \(l\) :
-
Quadrotor arm length (m)
- M :
-
Quadrotor mass (kg
- c :
-
Torque constant (m)
- \(I\) :
-
Inertia matrix (kg.m−2)
- \(f\) :
-
Thrust force (N)
- \(\eta\) :
-
Linear positions vector with respect to the earth frame
- \(\xi\) :
-
Linear velocities vector with respect to the body frame
- \(\varphi\) :
-
Roll angle (rad)
- \(\theta\) :
-
Pitch angle (rad)
- \(\psi\) :
-
Yaw angle (rad)
- \(\lambda\) :
-
Euler angles vector
- \(\Omega\) :
-
Angular velocities vector with respect to the body frame
References
Bouadi H, Bouchoucha M, Tadjine M (2007) Sliding mode control based on backstepping approach for an UAV type-quadrotor. World Acad Sci, Eng Tech 1(2):39–44
Cabecinhas D, Cunha R, Silvestre C (2014) A nonlinear quadrotor trajectory tracking controller with disturbance rejection. Control Eng Pract 26:1–10. https://doi.org/10.1016/j.conengprac.2013.12.017
Chovancová A et al (2016) Comparison of various quaternion-based control methods applied to quadrotor with disturbance observer and position estimator. Robot Auton Syst 79:87–98
Davoodi E, Rezaei M (2014) Dynamic modeling, simulation and control of a quadrotor using mems sensors’ experimental data. Modares Mech Eng 14(3):175–184
Emran BJ, Al-Omari M, Abdel-Hafez MF, Jaradat MA (2014) A cascaded approach for quadrotor’s attitude estimation. Procedia Technol 15:268–277. https://doi.org/10.1016/j.protcy.2014.09.080
Gonzalez A, Garcia P, Albertos P, Castillo P, Lozano R (2012) Robustness of a discrete-time predictor-based controller for time-varying measurement delay. Control Eng Pract 20(2):102–110. https://doi.org/10.1016/j.conengprac.2011.09.001
Guo K et al (2020) Multiple observers based anti-disturbance control for a quadrotor UAV against payload and wind disturbances. Control Eng Pract 102:104560
Hatamleh KS, Al-Shabi M, Al-Ghasem A, Asad A (2015) Unmanned aerial vehicles parameter estimation using artificial neural networks and iterative bi-section shooting method. Appl Soft Comput 36(3):457–467. https://doi.org/10.1016/j.asoc.2015.06.031
Lee D, Kim HJ, Sastry SH (2009) Feedback linearization vs adaptive sliding mode control for a quadrotor helicopter. Int J Control, Automat Sys 7(3):419–428
Li Sh, Wang Y, Tan J, Zheng Y (2016) Adaptive RBFNNs/Integral sliding mode control for a quadrotor aircraft. Neurocomputing 216:126–134. https://doi.org/10.1016/j.neucom.2016.07.033
Liu C, Xhen W, Andrews J (2012) Tracking control of small-scale helicopter using explicit MPC augmented with disturbance observers. Control Eng Pract 20(3):258–268. https://doi.org/10.1016/j.conengprac.2011.10.015
Liu H, Li D, Zuo Z, Zhong Y (2017) Robust attitude control for quadrotors with input time delays. Control Eng Pract 58:142–149. https://doi.org/10.1016/j.conengprac.2016.10.006
Luque L, Castillo B, Loukianov AG (2012) Robust block second order sliding mode control for a quadrotor. J Franklin Inst 349(2):719–739. https://doi.org/10.1016/j.jfranklin.2011.10.017
Masaud K, Macnab C (2014) Preventing bursting in adaptive control using an introspective neural network algorithm. Neurocomputing 136:300–314. https://doi.org/10.1016/j.neucom.2014.01.002
Mohebbi A, Achiche S, Baron L (2019) Integrated and concurrent detailed design of a mechatronic quadrotor system using a fuzzy-based particle swarm optimization. Eng Appl Artif Intell 82:192–206. https://doi.org/10.1016/j.engappai.2019.03.025
Noormohammadi-Asl A et al (2020) System identification and H∞-based control of quadrotor attitude. Mech Sys Signal Process 135:106358
Oner KT, Cetinsoy E, Sirimoglu E, Hancer C, Ayken T, Unel M, (2009) LQR and SMC stabilization of a new unmanned aerial vehicle. World Acad Sci, Eng Tech, 3(10):1190–1195. https://scholar.waset.org/1999.8/2009
Pitarch JL, Sala A (2014) Multicriteria fuzzy-polynomial observer design for a 3DoF nonlinear electromechanical platform. Eng Appl Artif Intell 30:96–106. https://doi.org/10.1016/j.engappai.2013.11.006
Palm W (2014) System dynamics, 3ed edn. Mc GraHill, NY
Sarabakha A, Imanberdiyev N, Kayacan E, Ahmadie M, Hagras H (2017) Novel levenberg–marquardt based learning algorithm for unmanned aerial vehicles. Inf Sci 417:361–380. https://doi.org/10.1016/j.ins.2017.07.020
Shirzadeh M, Jabbari H, Amirkhani A, Jalali AA (2017) Vision-based control of a quadrotor utilizing artificial neural networks for tracking of moving targets. Eng Appl Artif Intell 58:34–48. https://doi.org/10.1016/j.engappai.2016.10.016
Tran H, Chiou J (2016) PSO-based algorithm applied to quadcopter micro air vehicle controller design. Micromachines 7(9):168–175. https://doi.org/10.3390/mi7090168
Wu B, Han Sh, Xiao J, Hu X, Fan J (2016) Error compensation based on BP neural network for airborne laser ranging. Int J Light Electron Optics 127(8):4083–4088. https://doi.org/10.1016/j.ijleo.2016.01.066
Xiong J, Zhang G (2017) Global fast dynamic terminal sliding mode control for a quadrotor UAV. ISA Trans 66:233–240. https://doi.org/10.1016/j.isatra.2016.09.019
Yang Y, Yan Y (2016) Attitude regulation for unmanned quadrotors using adaptive fuzzy gain-scheduling sliding mode control. Aerosp Sci Technol 54:208–217. https://doi.org/10.1016/j.ast.2016.04.005
Acknowledgements
The authors wish to express their deep gratitude to the Shiraz University of Technology for providing research facilities and supports. A special thank is dedicated to Dr. T. Binazadeh from Electrical and Electronics Engineering Department at SUTech for her constructive comments and advices.
Author information
Authors and Affiliations
Corresponding author
Additional information
Technical Editor: Victor Juliano De Negri.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Farzaneh, M.M., Tavakolpour-Saleh, A.R. Stabilization of a quadrotor system using an optimal neural network controller. J Braz. Soc. Mech. Sci. Eng. 44, 26 (2022). https://doi.org/10.1007/s40430-021-03326-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40430-021-03326-5