Floating-Base Deep Lagrangian Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schulze, Lucas, Negri, Juliano Decico, Barasuol, Victor, Medeiros, Vivian Suzano, Becker, Marcelo, Peters, Jan, Arenz, Oleg
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918367057674240
author Schulze, Lucas
Negri, Juliano Decico
Barasuol, Victor
Medeiros, Vivian Suzano
Becker, Marcelo
Peters, Jan
Arenz, Oleg
author_facet Schulze, Lucas
Negri, Juliano Decico
Barasuol, Victor
Medeiros, Vivian Suzano
Becker, Marcelo
Peters, Jan
Arenz, Oleg
contents Grey-box methods for system identification combine deep learning with physics-informed constraints, capturing complex dependencies while improving out-of-distribution generalization. Despite the growing importance of floating-base systems such as humanoids and quadrupeds, current grey-box models ignore their specific physical constraints. For instance, the inertia matrix is not only positive definite but also exhibits branch-induced sparsity and input independence. Moreover, the 6x6 composite spatial inertia of the floating base inherits properties of single-rigid-body inertia matrices. As we show, this includes the triangle inequality on the eigenvalues of the composite rotational inertia. To address the lack of physical consistency in deep learning models of floating-base systems, we introduce a parameterization of inertia matrices that satisfies all these constraints. Inspired by Deep Lagrangian Networks (DeLaN), we train neural networks to predict physically plausible inertia matrices that minimize inverse dynamics error under Lagrangian mechanics. For evaluation, we collected and released a dataset on multiple quadrupeds and humanoids. In these experiments, our Floating-Base Deep Lagrangian Networks (FeLaN) achieve better overall performance on both simulated and real robots, while providing greater physical interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17270
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Floating-Base Deep Lagrangian Networks
Schulze, Lucas
Negri, Juliano Decico
Barasuol, Victor
Medeiros, Vivian Suzano
Becker, Marcelo
Peters, Jan
Arenz, Oleg
Robotics
Systems and Control
Grey-box methods for system identification combine deep learning with physics-informed constraints, capturing complex dependencies while improving out-of-distribution generalization. Despite the growing importance of floating-base systems such as humanoids and quadrupeds, current grey-box models ignore their specific physical constraints. For instance, the inertia matrix is not only positive definite but also exhibits branch-induced sparsity and input independence. Moreover, the 6x6 composite spatial inertia of the floating base inherits properties of single-rigid-body inertia matrices. As we show, this includes the triangle inequality on the eigenvalues of the composite rotational inertia. To address the lack of physical consistency in deep learning models of floating-base systems, we introduce a parameterization of inertia matrices that satisfies all these constraints. Inspired by Deep Lagrangian Networks (DeLaN), we train neural networks to predict physically plausible inertia matrices that minimize inverse dynamics error under Lagrangian mechanics. For evaluation, we collected and released a dataset on multiple quadrupeds and humanoids. In these experiments, our Floating-Base Deep Lagrangian Networks (FeLaN) achieve better overall performance on both simulated and real robots, while providing greater physical interpretability.
title Floating-Base Deep Lagrangian Networks
topic Robotics
Systems and Control
url https://arxiv.org/abs/2510.17270