EUVIMEDEUVIMED entdecken
Open Access

Deep Koopman Approach for Nonlinear Dynamics and Control of Tendon-Driven Continuum Robots

Navid Feizi, Filipe C Pedrosa, Jagadeesan Jayender, Rajni V Patel

IEEE Robotics and Automation Letters · 2025-03 · 10 (3) · 2926-2933

DOI: 10.1109/lra.2025.3533967 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Robotics and Automation Letters, 2025-03. Verfasst von Navid Feizi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Canadian Surgical Technologies and Advanced Robotics (CSTAR), London Health Sciences Centre, London, ON N6A 5A5, Canada, and with the School of Biome…. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDDK NIH HHS, NIBIB NIH HHS, Natural Sciences and Engineering Research Council of Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tendon-driven continuum robots (TDCRs) have received widespread attention in the medical domain due to their slender shape and flexibility. Modeling the dynamics of TDCRs involves continuum mechanics that result in nonlinear and computationally intensive models posing challenges for real-time control. In this work, we propose efficient, and controloriented modeling of the nonlinear dynamics of TDCRs leveraging the deep Koopman approach. This method transforms the states of the system into an intrinsic nonlinear manifold, where the autonomous dynamics are approximated linearly, and the actuation input enters the system with a bilinear term. The proposed model captures the nonlinearities, including space-dependent variations in the system spectrum. Position control is implemented using a linear quadratic controller, leveraging the linear nature of the Koopman operator. The accuracy of the proposed method is experimentally validated using a dualtendon robotic steerable catheter, achieving a position tracking error of 1.64 mm (SD = 0.74) for multi-sinusoidal, and 0.60 mm (SD = 0.30) for sinusoidal (0.05 Hz) target trajectories. The results demonstrate the potential for applying the proposed approach for real-time control of a broad range of TDCRs.

Schlagwörter

Stichwörter der Autor:innen

Deep KoopmanNonlinear DynamicsReal-time ControlRobotic CatheterTendon-driven Continuum Robot

Autor:innen und Institutionen

  • Canadian Surgical Technologies and Advanced Robotics (CSTAR), London Health Sciences Centre, London, ON N6A 5A5, Canada, and with the School of Biomedical Engineering, Western University, London, ON N6A 3K7, Canada.
  • CSTAR, and with the Department of Electrical and Computer Engineering, Western University.
  • Department of Radiology at Brigham and Women's Hospital, and Harvard Medical School, Boston, MA 02115, USA.
  • CSTAR, and with the Department of Electrical and Computer Engineering, the Department of Surgery, the Department of Clinical Neurological Sciences, and the School of Biomedical Engineering, Western University.

Förderung

  • NIDDK NIH HHS
  • NIBIB NIH HHS
  • Natural Sciences and Engineering Research Council of Canada
  • Canada Research Chairs
  • National Institute of Biomedical Imaging and Bioengineering of NIH

Zitieren

APA

Feizi, N., Pedrosa, F. C., Jayender, J., & Patel, R. V. (2025). Deep Koopman Approach for Nonlinear Dynamics and Control of Tendon-Driven Continuum Robots. IEEE Robotics and Automation Letters, 10(3), 2926-2933. https://doi.org/10.1109/lra.2025.3533967

Vancouver

Feizi N, Pedrosa FC, Jayender J, Patel RV. Deep Koopman Approach for Nonlinear Dynamics and Control of Tendon-Driven Continuum Robots. IEEE Robotics and Automation Letters. 2025;10(3):2926-2933. doi:10.1109/lra.2025.3533967

BibTeX
@article{Feizi2025,
  author = {Feizi, Navid and Pedrosa, Filipe C and Jayender, Jagadeesan and Patel, Rajni V},
  title = {Deep Koopman Approach for Nonlinear Dynamics and Control of Tendon-Driven Continuum Robots},
  journal = {IEEE Robotics and Automation Letters},
  year = {2025},
  volume = {10},
  number = {3},
  pages = {2926--2933},
  doi = {10.1109/lra.2025.3533967}
}
Kostenlos starten →