Novel Levenberg–Marquardt based learning algorithm for unmanned aerial vehicles

Andriy Sarabakha, Nursultan Imanberdiyev, Erdal Kayacan*, Mojtaba Ahmadieh Khanesar, Hani Hagras

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review


In this paper, Levenberg–Marquardt inspired sliding mode control theory based adaptation laws are proposed to train an intelligent fuzzy neural network controller for a quadrotor aircraft. The proposed controller is used to control and stabilize a quadrotor unmanned aerial vehicle in the presence of periodic wind gust. A proportional-derivative controller is firstly introduced based on which fuzzy neural network is able to learn the quadrotor's control model on-line. The proposed design allows handling uncertainties and lack of modelling at a computationally inexpensive cost. The parameter update rules of the learning algorithms are derived based on a Levenberg–Marquardt inspired approach, and the proof of the stability of two proposed control laws are verified by using the Lyapunov stability theory. In order to evaluate the performance of the proposed controllers extensive simulations and real-time experiments are conducted. The 3D trajectory tracking problem for a quadrotor is considered in the presence of time-varying wind conditions.

Original languageEnglish
JournalInformation Sciences
Pages (from-to)361-380
Number of pages20
Publication statusPublished - 1 Nov 2017
Externally publishedYes


  • Fuzzy neural networks
  • Levenberg–Marquardt algorithm
  • Sliding mode control
  • Type-1 fuzzy logic control
  • Unmanned aerial vehicle


Dive into the research topics of 'Novel Levenberg–Marquardt based learning algorithm for unmanned aerial vehicles'. Together they form a unique fingerprint.

Cite this