将机器人结构对称性融入图神经网络，提升动力学学习效率与泛化能力。
Morphological-Symmetry-Equivariant Heterogeneous Graph Neural Network for Robotic Dynamics Learning
- 利用机械结构与形态对称性作为约束，构建新型异质图网络
- 在真实与仿真四足机器人上验证，显著提升样本与模型效率
- 适用于多种多体系统，适合机器人动力学建模研究者
我们提出一种形态对称性等变的异质图神经网络（MS-HGNN），用于机器人动力学学习。该方法将机器人的运动学结构和形态对称性统一建模为图结构，通过将这些先验知识嵌入学习架构作为约束，确保高泛化性、高样本效率和模型效率。我们正式证明了所提MS-HGNN具备形态对称性等变性，并在真实世界与仿真数据上的多个四足机器人动力学学习任务中验证其有效性。代码已公开于https://github.com/lunarlab-gatech/MorphSym-HGNN/。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。