Intelligent Systems
Note: This research group has relocated.

Learning Constrained Dynamics with Gauss Principle adhering Gaussian Processes

2020

Conference Paper

ics


The identification of the constrained dynamics of mechanical systems is often challenging. Learning methods promise to ease an analytical analysis, but require considerable amounts of data for training. We propose to combine insights from analytical mechanics with Gaussian process regression to improve the model's data efficiency and constraint integrity. The result is a Gaussian process model that incorporates a priori constraint knowledge such that its predictions adhere to Gauss' principle of least constraint. In return, predictions of the system's acceleration naturally respect potentially non-ideal (non-)holonomic equality constraints. As corollary results, our model enables to infer the acceleration of the unconstrained system from data of the constrained system and enables knowledge transfer between differing constraint configurations.

Author(s): A. René Geist and Sebastian Trimpe
Book Title: Proceedings of the 2nd Conference on Learning for Dynamics and Control
Volume: 120
Pages: 225--234
Year: 2020
Month: June

Series: Proceedings of Machine Learning Research (PMLR)
Editors: Bayen, Alexandre M. and Jadbabaie, Ali and Pappas, George and Parrilo, Pablo A. and Recht, Benjamin and Tomlin, Claire and Zeilinger, Melanie
Publisher: PMLR

Department(s): Intelligent Control Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Event Name: 2nd Annual Conference on Learning for Dynamics and Control (L4DC)
Event Place: The Cloud

State: Published
URL: http://proceedings.mlr.press/v120/geist20a.html

Links: Proceedings of Machine Learning Research

BibTex

@inproceedings{gaussprinciple2020geist,
  title = {Learning Constrained Dynamics with Gauss Principle adhering Gaussian Processes},
  author = {Geist, A. René and Trimpe, Sebastian},
  booktitle = {Proceedings of the 2nd Conference on Learning for Dynamics and Control},
  volume = {120},
  pages = {225--234},
  series = {Proceedings of Machine Learning Research (PMLR)},
  editors = {Bayen, Alexandre M. and Jadbabaie, Ali and Pappas, George and Parrilo, Pablo A. and Recht, Benjamin and Tomlin, Claire and Zeilinger, Melanie},
  publisher = {PMLR},
  month = jun,
  year = {2020},
  doi = {},
  url = {http://proceedings.mlr.press/v120/geist20a.html},
  month_numeric = {6}
}