Model Estimation Ensuring Passivity by Using Port-Hamiltonian Model and Deep Learning

Authors

Hiroyasu Nakano, Ryo Ariizumi, Toru Asai, Shun-ichi Azuma

Abstract

An accurate model is necessary for highly accurate control, but it is not always easy to obtain the model via first principles. One of the methods for creating models is to represent the model by neural networks and train them in accordance with the data. However, the model created by machine learning cannot always satisfy the physical properties of the system. If some prior knowledge can be imposed on the estimation, it can be beneficial in the application of the obtained model and the reduction of the burden needed for the training. In this paper, we propose the new method to reflect the passivity of the system by using a port-Hamiltonian form. The effectiveness of the proposed method is shown via numerical examples.

Citation

• Journal: 2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)
• Year: 2022
• Volume:
• Issue:
• Pages: 886–891
• Publisher: IEEE
• DOI: 10.23919/sice56594.2022.9905855

BibTeX

@inproceedings{Nakano_2022,
  title={{Model Estimation Ensuring Passivity by Using Port-Hamiltonian Model and Deep Learning}},
  DOI={10.23919/sice56594.2022.9905855},
  booktitle={{2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)}},
  publisher={IEEE},
  author={Nakano, Hiroyasu and Ariizumi, Ryo and Asai, Toru and Azuma, Shun-ichi},
  year={2022},
  pages={886--891}
}

Download the bib file

References

• Zanchettin, A. M., Lacevic, B. & Rocco, P. A novel passivity-based control law for safe human-robot coexistence. 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems 2276–2281 (2012) doi:10.1109/iros.2012.6385797 – 10.1109/iros.2012.6385797
• zhongy, Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control. International Conference on Learning Representations (2020)
• Zhang, M., Borja, P., Ortega, R., Liu, Z. & Su, H. PID Passivity-Based Control of Port-Hamiltonian Systems. IEEE Trans. Automat. Contr. 63, 1032–1044 (2018) – 10.1109/tac.2017.2732283
• Aranovskiy, S., Ortega, R. & Cisneros, R. Robust PI passivity-based control of nonlinear systems: Application to port-Hamiltonian systems and temperature regulation. 2015 American Control Conference (ACC) 434–439 (2015) doi:10.1109/acc.2015.7170774 – 10.1109/acc.2015.7170774
• van der schaft, L2-Gain and Passivity Techniques in Nonlinear Control. (1996)
• meza, Analysis via Passivity Theory of a Class of Nonlinear PID Global Regulators for Robot Manipulators. Advances in PID Control (2011)
• greydanus, Hamiltonian Neural Networks. 33rd Conference on Neural Information Processing Systems (2019)
• Nguyen-Tuong, D. & Peters, J. Model learning for robot control: a survey. Cogn Process 12, 319–340 (2011) – 10.1007/s10339-011-0404-1