Closing the Sim-to-Real Gap with Physics-Enhanced Neural ODEs

Tobias Kamp, Johannes Ultsch, Jonathan Brembeck

2023

Abstract

A central task in engineering is the modelling of dynamical systems. In addition to first-principle methods, data-driven approaches leverage recent developments in machine learning to infer models from observations. Hybrid models aim to inherit the advantages of both, white- and black-box modelling approaches by combining the two methods in various ways. In this sense, Neural Ordinary Differential Equations (NODEs) proved to be a promising approach that deploys state-of-the-art ODE solvers and offers great modelling flexibility. In this work, an exemplary NODE setup is used to train low-dimensional artificial neural networks with physically meaningful outputs to enhance a dynamical model. The approach maintains the physical integrity of the model and offers the possibility to enforce physical laws during the training. Further, this work outlines how a confidence interval for the learned functions can be inferred based on the deployed training data. The robustness of the approach against noisy data and model uncertainties is investigated and a way to optimize model parameters alongside the neural networks is shown. Finally, the training routine is optimized with mini-batching and sub-sampling, which reduces the training duration in the given example by over 80 %.

Paper Citation

in Harvard Style

Kamp T., Ultsch J. and Brembeck J. (2023). Closing the Sim-to-Real Gap with Physics-Enhanced Neural ODEs. In Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO; ISBN 978-989-758-670-5, SciTePress, pages 77-84. DOI: 10.5220/0012160100003543

in Bibtex Style

@conference{icinco23,
author={Tobias Kamp and Johannes Ultsch and Jonathan Brembeck},
title={Closing the Sim-to-Real Gap with Physics-Enhanced Neural ODEs},
booktitle={Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO},
year={2023},
pages={77-84},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012160100003543},
isbn={978-989-758-670-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO
TI - Closing the Sim-to-Real Gap with Physics-Enhanced Neural ODEs
SN - 978-989-758-670-5
AU - Kamp T.
AU - Ultsch J.
AU - Brembeck J.
PY - 2023
SP - 77
EP - 84
DO - 10.5220/0012160100003543
PB - SciTePress