FEM-Validated Real-Time Modelling of Soft Tactile Deformation
FEM-Validated Real-Time Modelling of Soft Tactile Deformation
This research presents a data-efficient framework that combines limited real-world validation, high-fidelity FEM, and graph neural networks (GNNs) for accurate real-time prediction of two-dimensional tactile deformation in a planar soft tactile structure. The validated FEM model achieves sub-0.5 mm error in over 90% of validation cases, while the learned GNN surrogate reaches a mean absolute error of 0.32 mm with millisecond-scale inference, compared to minute-scale FEM simulation. The model demonstrates strong sim-to-real transfer and is integrated into a real-time visualization pipeline for virtual prototyping and design exploration.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
contact configurations
82
synthetic contact scenarios
768
mean absolute error
0.32
error
0.5
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ited real-world validation, high-fidelity FEM, and graph neural networks (GNNs) for accurate real-time prediction of two-dimensional tactile deformation in a planar soft tactile structure. The key idea is to decouple validation from training: 82 camera-tracked contact configurations are used only to tune and validate an ANSYS FEM model, which then generates 768 synthetic contact scenarios for GNN training. We evaluat
Open source S3
e both forward prediction from marker deformation to contact localisation and inverse inference from contact configuration to marker deformation. The validated FEM achieves sub-0.5 mm error in more than 90% of validation cases, while the learned GNN surrogate reaches a mean absolute error of 0.32 mm with millisecond-scale inference, compared with minute-scale FEM simulation. Models trained entirely on synthetic FEM d
Open source S4
ata retain sub-millimetre accuracy on real measurements from the 2D tactile structure, demonstrating strong sim-to-real transfer within the tested planar setting. We further integrate the learned model into a real-time visualisation pipeline, enabling rapid deformation prediction for virtual prototyping and simulator-based design exploration without extensive physical testing.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org