Neural network-based model predictive control for unmanned aerial vehicles

Yiwei  Zhou

doi:10.55092/aias20250005

Abstract

This study presents a neural network-based predictive control (abbreviated as NNMPC in subsequent content) approach for quadrotor tracking. By learning dynamical behaviors from experimental flight data, a neural ordinary differential model (NODM) is built first, which is particularly suitable for situations where aerodynamic conditions are complex and difficult to model formulaically. Subsequently, the NODM is used for designing the predictive control by considering the constraint conditions. Here, the proposed method uses a linearized model of the NODM established to effectively handle the neural network system for predicting the states, reducing the computation time. Finally, simulation results show that the proposed method can achieve a good tracking performance.

Keywords

model predictive control; neural ordinary differential equations; trajectory tracking; UAV

Preview

view pdf

References

[1]Mohsan SAH, Khan MA, Noor F, Ullah I, Alsharif MH. Towards the unmanned aerial vehicles (UAVs): a comprehensive review. Drones 2022, 6(6):147.
[2]Huang S, Teo RSH, Leong WWL. Multi-camera networks for coverage control of drones. Drones 2022, 6(3):67
[3]Huang S, Teo RSH, Tan KK. Collision avoidance of multi unmanned aerial vehicles: a review. Annu. Rev. Control 2019, 48:147–164
[4]Kamel M, Stastny T, Alexis K, Siegwart R. Model predictive control for trajectory tracking of unmanned aerial vehicles using robot operating system. In Robot Operating System (ROS): The Complete Reference (Volume 2), 1st ed. Cham: Springer International Publishing, 2017. pp. 3–39
[5]Richalet J, Rault A, Testud JL, Papon J. Model predictive heuristic control: applications to industrial processes. Automatica 1978, 14(5):413–428.
[6]Hang P, Huang S, Chen X, Tan KK. Path planning of collision avoidance for unmanned ground vehicles: a nonlinear model predictive control approach. Proc. Inst. Mech. Eng., Part I: J. Syst. Control Eng. 2021, 235(2):222–236.
[7]Zhang X, Ma J, Cheng Z, Huang S, Ge SS, et al. Trajectory generation by chance-constrained nonlinear MPC with probabilistic prediction. IEEE Trans. Cybern. 2021, 51(7):3616–3629.
[8]Cesari G, Schildbach G, Carvalho A, Borrelli F. Scenario model predictive control for lane change assistance and autonomous driving on highways. IEEE Intell. Transp. Syst. Mag. 2017, 9(3):23–35
[9]CamachoEF,BordonsC. Nonlinearmodelpredictive control: an introductory review. In Assessment and Future Directions of Nonlinear Model Predictive Control, 1st ed. Berlin: Springer Berlin Heidelberg, 2007. pp. 1–16.
[10]Zhou W, Chen S, Chang CW, Wen CY, Chen CK, et al. System identification and control for a tail-sitter unmanned aerial vehicle in the cruise flight. IEEE Access 2020, 8:218348–218359.
[11]Fay G. Derivation of the Aerodynamic Forces for the Mesicopter Simulation. Available: https: //media.gradebuddy.com/documents/340594/59482841-8400-4d1d-890d-8932a64a24d1.pdf (accessed on 28 May 2025).
[12]Ru P, Subbarao K. Nonlinear model predictive control for unmanned aerial vehicles. Aerospace 2017, 4(2):31
[13]Jiang B, Li B, Zhou W, Lo LY, Chen CK, et al. Neural network based model predictive control for a quadrotor UAV. Aerospace 2022, 9(8):460.
[14]Liu S, Wang J. A simplified dual neural network for quadratic programming with its KWTA application. IEEE Trans. Neural Networks 2006, 17(6):1500–1510.
[15]Bansal S, Akametalu AK, Jiang FJ, Laine F, Tomlin CJ. Learning quadrotor dynamics using neural network for flight control. In 2016 IEEE 55th Conference on Decision and Control (CDC), Las Vegas, USA, December 12–14, 2016, pp. 4653–4660.
[16]Torrente G, Kaufmann E, Föhn P, Scaramuzza D. Data-driven MPC for quadrotors. IEEE Rob. Autom. Lett. 2021, 6(2):3769–3776.
[17]Zhang L, Huang S, Xiang C, Teo R, Srigrarom S, et al. AI-based adaptive nonlinear MPC for quadrotors. In 2024 International Conference on Unmanned Aircraft Systems (ICUAS), Chania, Greece, June 4–7, 2024, pp. 216–223.
[18]Chen RTQ, Rubanova Y, Bettencourt J, Duvenaud D. Neural ordinary differential equations. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montréal, Canada, December 2–8, 2018, pp. 6572–6583.
[19] Panagiotou P, Kaparos P, Salpingidou C, Yakinthos K. Aerodynamic design of a MALE UAV. Aerosp. Sci. Technol. 2016, 50:127–138.
[20]Huang S, Tan KK, Lee TH. Applied predictive control, 1st ed. London: Springer London, 2013. pp. 1–264.
[21]Akima H. A new method of interpolation and smooth curve fitting based on local procedures. J. ACM 1970, 17(4):589–602