Learning-Augmented IDA–PBC for Underactuated Mechanical Systems with Unmeasured Actuator Dynamics and Unmatched Disturbances

Authors

Abstract

Underactuated mechanical systems (UMSs) present significant challenges in control design due to limited actuation, nonlinear coupling, and susceptibility to unmatched and time-varying disturbances. Traditional passivity-based methods often assume full state availability and matched disturbances, limiting their applicability in uncertain, sensor-constrained environments. This study proposes a learning-augmented interconnection and damping assignment passivity-based control (iIDA–PBC) framework that enhances robustness and adaptability for UMSs. The approach integrates real-time disturbance estimation using Gaussian Math. Comput. Appl. (GPR) and Math. Comput. Appl. (LSTM) networks, alongside nonlinear observer designs for reconstructing unmeasured actuator states. The overall control architecture preserves the port-Hamiltonian structure while enabling adaptive compensation for unknown external perturbations. Theoretical analysis ensures Math. Comput. Appl. (ISS) under bounded estimation errors. Simulation results on a benchmark underactuated system demonstrate improved disturbance rejection, tracking accuracy, and robustness compared to conventional adaptive and passivity-based controllers. The proposed method is suitable for complex, partially observable systems such as aerial vehicles, autonomous robots, and marine platforms.

Keywords

adaptive control, disturbance observer, gpr, lstm, nonlinear observer, passivity-based control, port-hamiltonian systems, underactuated systems

Citation

Journal: Automation and Remote Control
Year: 2025
Volume: 86
Issue: 9-12
Pages: 305–321
Publisher: Pleiades Publishing Ltd
DOI: 10.1134/s0005117925600922

BibTeX

@article{Can_2025,
  title={{Learning-Augmented IDA–PBC for Underactuated Mechanical Systems with Unmeasured Actuator Dynamics and Unmatched Disturbances}},
  volume={86},
  ISSN={1608-3032},
  DOI={10.1134/s0005117925600922},
  number={9-12},
  journal={Automation and Remote Control},
  publisher={Pleiades Publishing Ltd},
  author={Can, Erol},
  year={2025},
  pages={305--321}
}

Download the bib file

References

Liu X, Shao H, Liu C, Li N, Guo X, Zheng F, Sun L (2023) An Adaptive Controller Based on Interconnection and Damping Assignment Passivity-Based Control for Underactuated Mechanical Systems: Application to the Ball and Beam System. Actuators 12(11):408. https://doi.org/10.3390/act1211040 – 10.3390/act12110408
Franco E (2023) Integral passivity‐based control of underactuated mechanical systems with actuator dynamics and constant disturbances. Intl J Robust & Nonlinear 33(16):10024–10045. https://doi.org/10.1002/rnc.688 – 10.1002/rnc.6885
Reiss J (2018) Model reduction for convective problems: formulation and application. IFAC-PapersOnLine 51(2):186–189. https://doi.org/10.1016/j.ifacol.2018.03.03 – 10.1016/j.ifacol.2018.03.032
Wang J, Zhou Q, Zheng W, Shao J (2024) Passivity-Based Control with Disturbance Observer of Electromagnetic Formation Flight Spacecraft in the Port-Hamiltonian Framework. Applied Sciences 14(10):4248. https://doi.org/10.3390/app1410424 – 10.3390/app14104248
M. Le, Acta Autom. Sin. (2021)
Kocijan J, Grancharova A (2014) Application of Gaussian Processes to the Modelling and Control in Process Engineering. Studies in Computational Intelligence 155–19 – 10.1007/978-3-662-43370-6_6
Zucco JPT, Ramirez H, Wu Y, Le Gorrec Y (2023) Linear Matrix Inequality Design of Exponentially Stabilizing Observer-Based State Feedback Port-Hamiltonian Controllers. IEEE Trans Automat Contr 68(10):6184–6191. https://doi.org/10.1109/tac.2022.322792 – 10.1109/tac.2022.3227927
Jiang H, Yu H, Jiang J, Tang S, Xie X (2025) An adaptive sampling method for generating boundary scenarios of UAV swarms based on Gaussian process regression. IET Conf Proc 2024(12):499–506. https://doi.org/10.1049/icp.2024.350 – 10.1049/icp.2024.3503
Kahraman S, Bacher R (2021) A comprehensive review of hyperspectral data fusion with lidar and sar data. Annual Reviews in Control 51:236–253. https://doi.org/10.1016/j.arcontrol.2021.03.00 – 10.1016/j.arcontrol.2021.03.003
Zheng W, Li J, Guo J, Du Y (2024) A Flexible Imitation Learning System Based on the Lyapunov Energy Function of the Neural Networks. 2024 IEEE International Conference on Industrial Technology (ICIT) 1– – 10.1109/icit58233.2024.10540837