Dynamics Harmonic Analysis of Robotic Systems: Application in Data-Driven Koopman Modelling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ordoñez-Apraez, Daniel, Kostic, Vladimir, Turrisi, Giulio, Novelli, Pietro, Mastalli, Carlos, Semini, Claudio, Pontil, Massimiliano
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916273576738816
author Ordoñez-Apraez, Daniel
Kostic, Vladimir
Turrisi, Giulio
Novelli, Pietro
Mastalli, Carlos
Semini, Claudio
Pontil, Massimiliano
author_facet Ordoñez-Apraez, Daniel
Kostic, Vladimir
Turrisi, Giulio
Novelli, Pietro
Mastalli, Carlos
Semini, Claudio
Pontil, Massimiliano
contents We introduce the use of harmonic analysis to decompose the state space of symmetric robotic systems into orthogonal isotypic subspaces. These are lower-dimensional spaces that capture distinct, symmetric, and synergistic motions. For linear dynamics, we characterize how this decomposition leads to a subdivision of the dynamics into independent linear systems on each subspace, a property we term dynamics harmonic analysis (DHA). To exploit this property, we use Koopman operator theory to propose an equivariant deep-learning architecture that leverages the properties of DHA to learn a global linear model of the system dynamics. Our architecture, validated on synthetic systems and the dynamics of locomotion of a quadrupedal robot, exhibits enhanced generalization, sample efficiency, and interpretability, with fewer trainable parameters and computational costs.
format Preprint
id arxiv_https___arxiv_org_abs_2312_07457
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Dynamics Harmonic Analysis of Robotic Systems: Application in Data-Driven Koopman Modelling
Ordoñez-Apraez, Daniel
Kostic, Vladimir
Turrisi, Giulio
Novelli, Pietro
Mastalli, Carlos
Semini, Claudio
Pontil, Massimiliano
Robotics
Artificial Intelligence
Machine Learning
Systems and Control
43-08
We introduce the use of harmonic analysis to decompose the state space of symmetric robotic systems into orthogonal isotypic subspaces. These are lower-dimensional spaces that capture distinct, symmetric, and synergistic motions. For linear dynamics, we characterize how this decomposition leads to a subdivision of the dynamics into independent linear systems on each subspace, a property we term dynamics harmonic analysis (DHA). To exploit this property, we use Koopman operator theory to propose an equivariant deep-learning architecture that leverages the properties of DHA to learn a global linear model of the system dynamics. Our architecture, validated on synthetic systems and the dynamics of locomotion of a quadrupedal robot, exhibits enhanced generalization, sample efficiency, and interpretability, with fewer trainable parameters and computational costs.
title Dynamics Harmonic Analysis of Robotic Systems: Application in Data-Driven Koopman Modelling
topic Robotics
Artificial Intelligence
Machine Learning
Systems and Control
43-08
url https://arxiv.org/abs/2312.07457