iFEM2.0: Dense 3-D Contact Force Field Reconstruction and Assessment for Vision-Based Tactile Sensors

CanZhao, Jin Liu, Daolin Ma

Keywords: Force and tactile sensing, inverse finite-element method (iFEM), vision-based tactile sensors

TL;DR: This approach utilizes a multilayer inverse finite element method (iFEM2.0) to reconstruct dense 3D contact force distributions, which is crucial for tasks like dexterous robotic manipulation.

Abstract: Vision-based tactile sensors offer rich tactile infor- mation through high-resolution tactile images, enabling the re- construction of dense contact force fields on the sensor surface. However, accurately reconstructing the 3-D contact force distri- bution remains a challenge. In this article, we propose the mul- tilayer inverse finite-element method (iFEM2.0) as a robust and generalized approach to reconstruct dense contact force distri- bution. We systematically analyze various parameters within the iFEM2.0 framework, and determine the appropriate parameter combinations through simulation and in situ mechanical calibra- tion. Our approach incorporates multilayer mesh constraints and ridge regularization to enhance robustness. Furthermore, as no off-the-shelf measurement equipment or criterion metrics exist for 3-D contact force distribution perception, we present a benchmark covering accuracy, fidelity, and noise resistance that can serve as a cornerstone for other future force distribution reconstruction methods. The proposed iFEM2.0 demonstrates good performance in both simulation- and experiment-based evaluations. Such dense 3-D contact force information is critical for enabling dexterous robotic manipulation that handles both rigid and soft materials.

Submission Number: 1