Tensegrity Robot Endcap-Ground Contact Estimation with Symmetry-aware Heterogeneous Graph Neural Network

TL;DR

This paper presents a symmetry-aware heterogeneous graph neural network that estimates ground contact states in tensegrity robots using only proprioceptive data, significantly improving accuracy and efficiency over existing methods.

Contribution

The introduction of Sym-HGNN that leverages robot symmetry for better contact estimation without dedicated sensors, enhancing state estimation in tensegrity robots.

Findings

Achieves up to 15% higher accuracy than CNN and MI-HGNN baselines.

Uses only 20% of training data compared to baselines.

Maintains low-drift, physically consistent state estimates.

Abstract

Tensegrity robots possess lightweight and resilient structures but present significant challenges for state estimation due to compliant and distributed ground contacts. This paper introduces a symmetry-aware heterogeneous graph neural network (Sym-HGNN) that infers contact states directly from proprioceptive measurements, including IMU and cable-length histories, without dedicated contact sensors. The network incorporates the robot's dihedral symmetry $D_3$ into the message-passing process to enhance sample efficiency and generalization. The predicted contacts are integrated into a state-of-the-art contact-aided invariant extended Kalman filter (InEKF) for improved pose estimation. Simulation results demonstrate that the proposed method achieves up to 15% higher accuracy and 5% higher F1-score using only 20% of the training data compared to the CNN and MI-HGNN baselines, while maintaining low-drift and physically consistent state estimation results comparable to ground truth contacts. This work highlights the potential of fully proprioceptive sensing for accurate and robust state estimation in tensegrity robots. Code available at: https://github.com/Jonathan-Twz/Tensegrity-Sym-HGNN