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

2026-03-02

AI Summary

This work addresses the challenge of accurate state estimation in tensegrity robots, which arises from their inherent flexibility and distributed contact dynamics. To overcome this, the authors propose a symmetry-aware heterogeneous graph neural network (Sym-HGNN) that leverages proprioceptive data—such as IMU readings and cable lengths—to directly infer contact states between the end caps and the ground. These contact predictions are then integrated into a contact-aided Invariant Extended Kalman Filter (InEKF) to enhance pose estimation accuracy. Notably, this is the first approach to embed D₃ symmetry into the message-passing mechanism of a graph neural network, substantially improving sample efficiency and generalization. Using only 20% of the training data, Sym-HGNN outperforms CNN and MI-HGNN baselines by 15% in contact estimation accuracy and 5% in F1 score, while achieving low pose drift and high physical consistency, closely matching real-world contact performance.

Technology Category

• Intelligent Robots: State Estimation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

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

Problem

• tensegrity robot
• contact estimation
• state estimation
• proprioceptive sensing
• ground contact

Innovation

• Symmetry-aware Heterogeneous Graph Neural Network
• Tensegrity Robot
• Contact State Estimation
• Proprioceptive Sensing
• Invariant Extended Kalman Filter