EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust Two-Wheeled Inverted Pendulum Trajectory Tracking and Control Using Adaptive Neural Networks With Feedback Linearization

Jorge Montoya-Cháirez, Alfredo Delgado-Spíndola, Isaac Gandarilla, Víctor Santibáñez, Eusebio Bugarin, Javier Moreno-Valenzuela

IEEE Access · 2026 · 14 · 79740-79756

DOI: 10.1109/access.2026.3693757 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Jorge Montoya-Cháirez und 5 weiteren Autor:innen. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Tecnologico de Monterrey, RICCA od TecNM, SECIHTI.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this work, a robust adaptive neural network controller is proposed for tracking control of the displacement and orientation, while keeping the pendulum in the upright position, of a two-wheeled inverted pendulum system. The proposed approach is designed to be compatible with commercial robotic platforms, which typically employ velocity control signals rather than torque or voltage inputs and provide limited access to inner control layers. Accordingly, the proposed control architecture consists of an inaccessible embedded velocity-control loop, which operates as a closed-box subsystem, and an outer adaptive controller that generates the reference velocity commands for the embedded system. To this end, an adaptive neural network controller is designed to achieve the control objectives using acceleration signals, which are subsequently integrated before being applied to the system. Finally, in addition to the stability proof, the effectiveness of the proposed controller is validated through real-time experiments on the RAB-ITLAG-2 platform and compared with a model based, proportional derivative and neuro-fuzzy controllers. The numerical results, including the root mean square, standard deviation, and peak values of the tracking errors, demonstrate the superior performance of the proposed method in the presence of model uncertainties and external disturbances.

Förderung

  • Tecnologico de Monterrey
  • RICCA od TecNM
  • SECIHTI

Zitieren

APA

Montoya-Cháirez, J., Delgado-Spíndola, A., Gandarilla, I., Santibáñez, V., Bugarin, E., & Moreno-Valenzuela, J. (2026). Robust Two-Wheeled Inverted Pendulum Trajectory Tracking and Control Using Adaptive Neural Networks With Feedback Linearization. IEEE Access, 14, 79740-79756. https://doi.org/10.1109/access.2026.3693757

Vancouver

Montoya-Cháirez J, Delgado-Spíndola A, Gandarilla I, Santibáñez V, Bugarin E, Moreno-Valenzuela J. Robust Two-Wheeled Inverted Pendulum Trajectory Tracking and Control Using Adaptive Neural Networks With Feedback Linearization. IEEE Access. 2026;14:79740-79756. doi:10.1109/access.2026.3693757

BibTeX
@article{MontoyaChirez2026,
  author = {Montoya-Cháirez, Jorge and Delgado-Spíndola, Alfredo and Gandarilla, Isaac and Santibáñez, Víctor and Bugarin, Eusebio and Moreno-Valenzuela, Javier},
  title = {Robust Two-Wheeled Inverted Pendulum Trajectory Tracking and Control Using Adaptive Neural Networks With Feedback Linearization},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {79740--79756},
  doi = {10.1109/access.2026.3693757}
}
Kostenlos starten →