English

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.

Keywords

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}
}
R2 v1 2026-06-28T13:07:34.256Z