We present Sparsh-skin, a pre-trained encoder for magnetic skin sensors distributed across the fingertips, phalanges, and palm of a dexterous robot hand. Magnetic tactile skins offer a flexible form factor for hand-wide coverage with fast response times, in contrast to vision-based tactile sensors that are restricted to the fingertips and limited by bandwidth. Full hand tactile perception is crucial for robot dexterity. However, a lack of general-purpose models, challenges with interpreting magnetic flux and calibration have limited the adoption of these sensors. Sparsh-skin, given a history of kinematic and tactile sensing across a hand, outputs a latent tactile embedding that can be used in any downstream task. The encoder is self-supervised via self-distillation on a variety of unlabeled hand-object interactions using an Allegro hand sensorized with Xela uSkin. In experiments across several benchmark tasks, from state estimation to policy learning, we find that pretrained Sparsh-skin representations are both sample efficient in learning downstream tasks and improve task performance by over 41% compared to prior work and over 56% compared to end-to-end learning.
View on arXiv@article{sharma2025_2505.11420,
title={ Self-supervised perception for tactile skin covered dexterous hands },
author={ Akash Sharma and Carolina Higuera and Chaithanya Krishna Bodduluri and Zixi Liu and Taosha Fan and Tess Hellebrekers and Mike Lambeta and Byron Boots and Michael Kaess and Tingfan Wu and Francois Robert Hogan and Mustafa Mukadam },
journal={arXiv preprint arXiv:2505.11420},
year={ 2025 }
}