One-shot backpropagation for multi-step prediction in physics-based system identification -- EXTENDED VERSION
Systems and Control
2025-06-06 v2 Machine Learning
Systems and Control
Abstract
The aim of this paper is to present a novel physics-based framework for the identification of dynamical systems, in which the physical and structural insights are reflected directly into a backpropagation-based learning algorithm. The main result is a method to compute in closed form the gradient of a multi-step loss function, while enforcing physical properties and constraints. The derived algorithm has been exploited to identify the unknown inertia matrix of a space debris, and the results show the reliability of the method in capturing the physical adherence of the estimated parameters.
Cite
@article{arxiv.2310.20567,
title = {One-shot backpropagation for multi-step prediction in physics-based system identification -- EXTENDED VERSION},
author = {Cesare Donati and Martina Mammarella and Fabrizio Dabbene and Carlo Novara and Constantino Lagoa},
journal= {arXiv preprint arXiv:2310.20567},
year = {2025}
}