MI-HGNN: Morphology-Informed Heterogeneous Graph Neural Network for Legged Robot Contact Perception

📅 2024-09-17
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses three key challenges in contact sensing for legged robots: poor generalization, low sample efficiency, and model redundancy. To this end, we propose Morphology-Informed Heterogeneous Graph Neural Networks (MI-HGNN). Methodologically, we explicitly represent the robot’s rigid-body topology—as a heterogeneous graph where joints serve as nodes and links as edges—and incorporate morphological constraints and dynamics priors to achieve seamless integration of model-based knowledge and data-driven learning. Compared to state-of-the-art methods relying on morphological symmetry, MI-HGNN achieves an 8.4% improvement in accuracy while reducing parameter count to just 0.21%. Trained jointly on multi-source simulation and real-robot data, the method significantly enhances robustness and cross-scenario generalization. Experimental validation on a physical quadruped platform confirms its effectiveness and practical deployability.

Technology Category

Application Category

📝 Abstract
We present a Morphology-Informed Heterogeneous Graph Neural Network (MI-HGNN) for learning-based contact perception. The architecture and connectivity of the MI-HGNN are constructed from the robot morphology, in which nodes and edges are robot joints and links, respectively. By incorporating the morphology-informed constraints into a neural network, we improve a learning-based approach using model-based knowledge. We apply the proposed MI-HGNN to two contact perception problems, and conduct extensive experiments using both real-world and simulated data collected using two quadruped robots. Our experiments demonstrate the superiority of our method in terms of effectiveness, generalization ability, model efficiency, and sample efficiency. Our MI-HGNN improved the performance of a state-of-the-art model that leverages robot morphological symmetry by 8.4% with only 0.21% of its parameters. Although MI-HGNN is applied to contact perception problems for legged robots in this work, it can be seamlessly applied to other types of multi-body dynamical systems and has the potential to improve other robot learning frameworks. Our code is made publicly available at https://github.com/lunarlab-gatech/Morphology-Informed-HGNN.
Problem

Research questions and friction points this paper is trying to address.

Enhancing contact perception in legged robots
Integrating robot morphology into neural networks
Improving efficiency and generalization in robot learning
Innovation

Methods, ideas, or system contributions that make the work stand out.

Morphology-Informed Heterogeneous Graph Neural Network
Model-based knowledge integration
Enhanced contact perception accuracy
🔎 Similar Papers
No similar papers found.
D
Daniel Butterfield
Georgia Institute of Technology, Atlanta, GA 30332, USA
S
S. S. Garimella
Georgia Institute of Technology, Atlanta, GA 30332, USA
N
Nai-Jen Cheng
Georgia Institute of Technology, Atlanta, GA 30332, USA
L
Lu Gan
Georgia Institute of Technology, Atlanta, GA 30332, USA