Morphological-Symmetry-Equivariant Heterogeneous Graph Neural Network for Robotic Dynamics Learning

Fengze Xie*1, Sizhe Wei*2, Yue Song1, Yisong Yue1, Lu Gan2
1California Institute of Technology 2Georgia Institute of Technology
*Indicates Equal Contribution
Paper Code arXiv
Mini Cheetah K4 Symmetry

Mini-Cheetah exhibiting K4 symmetry properties

SOLO C2 Symmetry

A1 robot demonstrating C2 symmetry properties

Method Overview

Method Overview

Overview of our MorphSym-HGNN architecture incorporating morphological symmetries for robotic dynamics learning.

Abstract

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.

BibTeX

@misc{xie2024morphologicalsymmetryequivariantheterogeneousgraphneural,
        title={Morphological-Symmetry-Equivariant Heterogeneous Graph Neural Network for Robotic Dynamics Learning}, 
        author={Fengze Xie and Sizhe Wei and Yue Song and Yisong Yue and Lu Gan},
        year={2024},
        eprint={2412.01297},
        archivePrefix={arXiv},
        primaryClass={cs.RO},
        url={https://arxiv.org/abs/2412.01297}, 
  }