# TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensors

arXiv: https://arxiv.org/abs/1901.06181 · HTML: https://mlsanity.com/paper/1901.06181/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2019.

## Built on by (most cited first, 17 of 17)

- [Graph Neural Networks in IoT: A Survey](https://mlsanity.com/paper/2203.15935/) (2022)
- [Visuo-Haptic Object Perception for Robots: An Overview](https://mlsanity.com/paper/2203.11544/) (2022)
- [Hierarchical Graph Neural Networks for Proprioceptive 6D Pose Estimation of In-hand Objects](https://mlsanity.com/paper/2306.15858/) (2023)
- [HyperTaxel: Hyper-Resolution for Taxel-Based Tactile Signals Through Contrastive Learning](https://mlsanity.com/paper/2408.08312/) (2024)
- [Graph learning in robotics: a survey](https://mlsanity.com/paper/2310.04294/) (2023)
- [GraNet: A Multi-Level Graph Network for 6-DoF Grasp Pose Generation in Cluttered Scenes](https://mlsanity.com/paper/2312.03345/) (2023)
- [PyTouch: A Machine Learning Library for Touch Processing](https://mlsanity.com/paper/2105.12791/) (2021)
- [Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning](https://mlsanity.com/paper/2606.11767/) (2026)
- [Transferring Tactile Data Across Sensors](https://mlsanity.com/paper/2410.14310/) (2024)
- [ACROSS: A Deformation-Based Cross-Modal Representation for Robotic Tactile Perception](https://mlsanity.com/paper/2411.08533/) (2024)
- [Grasp Like Humans: Learning Generalizable Multi-Fingered Grasping from Human Proprioceptive Sensorimotor Integration](https://mlsanity.com/paper/2509.08354/) (2025)
- [Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradients](https://mlsanity.com/paper/2605.27412/) (2026)
- [Relational Mimic for Visual Adversarial Imitation Learning](https://mlsanity.com/paper/1912.08444/) (2019)
- [The Role of Tactile Sensing for Learning Reach and Grasp](https://mlsanity.com/paper/2502.20367/) (2025)
- [Quantization Meets Spikes: Nearly Lossless Conversion at the First Timestep via Polarity Multi-Spike Mapping](https://mlsanity.com/paper/2508.14520/) (2025)
- [Tactile Memory with Soft Robot: Robust Object Insertion via Masked Encoding and Soft Wrist](https://mlsanity.com/paper/2601.19275/) (2026)
- [Proximity3D: Shape from Capacitive Proximity on Sensing Manifold](https://mlsanity.com/paper/2608.30344/) (2026)

## Abstract (arXiv)

Tactile sensors provide useful contact data during the interaction with an object which can be used to accurately learn to determine the stability of a grasp. Most of the works in the literature represented tactile readings as plain feature vectors or matrix-like tactile images, using them to train machine learning models. In this work, we explore an alternative way of exploiting tactile information to predict grasp stability by leveraging graph-like representations of tactile data, which preserve the actual spatial arrangement of the sensor's taxels and their locality. In experimentation, we trained a Graph Neural Network to binary classify grasps as stable or slippery ones. To train such network and prove its predictive capabilities for the problem at hand, we captured a novel dataset of approximately 5000 three-fingered grasps across 41 objects for training and 1000 grasps with 10 unknown objects for testing. Our experiments prove that this novel approach can be effectively used to predict grasp stability.