Saved in:
Bibliographic Details
Main Authors: Xie, Fengze, Wei, Sizhe, Song, Yue, Yue, Yisong, Gan, Lu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.01297
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914380315099136
author Xie, Fengze
Wei, Sizhe
Song, Yue
Yue, Yisong
Gan, Lu
author_facet Xie, Fengze
Wei, Sizhe
Song, Yue
Yue, Yisong
Gan, Lu
contents We present a morphological-symmetry-equivariant heterogeneous graph neural network, namely MS-HGNN, for robotic dynamics learning, that integrates robotic kinematic structures and morphological symmetries into a single graph network. These structural priors are embedded into the learning architecture as constraints, ensuring high generalizability, sample and model efficiency. The proposed MS-HGNN is a versatile and general architecture that is applicable to various multi-body dynamic systems and a wide range of dynamics learning problems. We formally prove the morphological-symmetry-equivariant property of our MS-HGNN and validate its effectiveness across multiple quadruped robot learning problems using both real-world and simulated data. Our code is made publicly available at https://github.com/lunarlab-gatech/MorphSym-HGNN/.
format Preprint
id arxiv_https___arxiv_org_abs_2412_01297
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Morphological-Symmetry-Equivariant Heterogeneous Graph Neural Network for Robotic Dynamics Learning
Xie, Fengze
Wei, Sizhe
Song, Yue
Yue, Yisong
Gan, Lu
Robotics
Machine Learning
We present a morphological-symmetry-equivariant heterogeneous graph neural network, namely MS-HGNN, for robotic dynamics learning, that integrates robotic kinematic structures and morphological symmetries into a single graph network. These structural priors are embedded into the learning architecture as constraints, ensuring high generalizability, sample and model efficiency. The proposed MS-HGNN is a versatile and general architecture that is applicable to various multi-body dynamic systems and a wide range of dynamics learning problems. We formally prove the morphological-symmetry-equivariant property of our MS-HGNN and validate its effectiveness across multiple quadruped robot learning problems using both real-world and simulated data. Our code is made publicly available at https://github.com/lunarlab-gatech/MorphSym-HGNN/.
title Morphological-Symmetry-Equivariant Heterogeneous Graph Neural Network for Robotic Dynamics Learning
topic Robotics
Machine Learning
url https://arxiv.org/abs/2412.01297