Structure-Preserving Learning of Nonholonomic Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Beckers, Thomas, Bloch, Anthony, Colombo, Leonardo
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915897399050240
author Beckers, Thomas
Bloch, Anthony
Colombo, Leonardo
author_facet Beckers, Thomas
Bloch, Anthony
Colombo, Leonardo
contents Data-driven modeling is playing an increasing role in robotics and control, yet standard learning methods typically ignore the geometric structure of nonholonomic systems. As a consequence, the learned dynamics may violate the nonholonomic constraints and produce physically inconsistent motions. In this paper, we introduce a structure-preserving Gaussian process (GP) framework for learning nonholonomic dynamics. Our main ingredient is a nonholonomic matrix-valued kernel that incorporates the constraint distribution directly into the GP prior. This construction ensures that the learned vector field satisfies the nonholonomic constraints for all inputs. We show that the proposed kernel is positive semidefinite, characterize its associated reproducing kernel Hilbert space as a space of admissible vector fields, and prove that the resulting estimator admits a coordinate representation adapted to the constraint distribution. We also establish the consistency of the learned model. Numerical simulations on a vertical rolling disk illustrate the effectiveness of the proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27580
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Structure-Preserving Learning of Nonholonomic Dynamics
Beckers, Thomas
Bloch, Anthony
Colombo, Leonardo
Systems and Control
Mathematical Physics
Dynamical Systems
Data-driven modeling is playing an increasing role in robotics and control, yet standard learning methods typically ignore the geometric structure of nonholonomic systems. As a consequence, the learned dynamics may violate the nonholonomic constraints and produce physically inconsistent motions. In this paper, we introduce a structure-preserving Gaussian process (GP) framework for learning nonholonomic dynamics. Our main ingredient is a nonholonomic matrix-valued kernel that incorporates the constraint distribution directly into the GP prior. This construction ensures that the learned vector field satisfies the nonholonomic constraints for all inputs. We show that the proposed kernel is positive semidefinite, characterize its associated reproducing kernel Hilbert space as a space of admissible vector fields, and prove that the resulting estimator admits a coordinate representation adapted to the constraint distribution. We also establish the consistency of the learned model. Numerical simulations on a vertical rolling disk illustrate the effectiveness of the proposed approach.
title Structure-Preserving Learning of Nonholonomic Dynamics
topic Systems and Control
Mathematical Physics
Dynamical Systems
url https://arxiv.org/abs/2603.27580