TacPrint: A Wearable Fingertip Tactile Sensor for Human-to-Robot Contact Reproduction

2026-07-31

AI Summary

This work addresses the challenge of reliably capturing fine fingertip contact without interference under low-cost and scalable constraints—a key bottleneck in human-to-robot tactile skill transfer. The authors propose TacPrint, a wearable fingertip sensor featuring micro-dome structures on the inner surface of silicone aligned with a 24-channel capacitive sensing array, integrated within a real-sim-real mapping framework. This approach enables, for the first time, high-fidelity reconstruction of high-resolution contact depth maps from sparse capacitive signals. Experimental results demonstrate a contact region RMSE of 0.223 mm and an IoU of 0.829. In grasping and wiping tasks, tactile guidance improved success rates to 91.67% and 90%, respectively, with closed-loop grasping under edge contact achieving an 85% success rate—significantly outperforming baseline methods.

Abstract

Human-centric data collection is emerging as a significant paradigm for robot skill acquisition, but seamlessly integrating low-cost, scalable tactile sensing systems that capture fine-grained fingertip interactions without compromising natural operation remains a key challenge. This reduces the reliability of human-to-robot transfer in contact-rich tasks. In this work, we present TacPrint, a wearable fingertip tactile sensor, where protrusions on the inner surface of the silicone skin are aligned one-to-one with 24 capacitive taxels to enable localized capacitive responses. A real-to-sim-to-real pipeline estimates a 35 $\times$ 26 contact-depth map from 24-channel capacitive signals. Against simulation-generated labels, the model achieved a contact-region RMSE of 0.223 $\pm$ 0.161 mm, a weighted-centroid error of 1.213 $\pm$ 2.379 pixels, and an IoU of 0.829 $\pm$ 0.169. With measured capacitive inputs, the network-predicted depth evaluated at the guide-calibrated contact center showed a mean absolute error of 0.085 $\pm$ 0.057 mm across all 40 controlled trials, while the mean contact-position error was 0.250 $\pm$ 0.208 mm across the 37 trials whose reference contact regions were not truncated by the sensing boundary. In human-to-robot replay, tactile-guided compensation increased grasping and wiping success rates from 0% to 91.67% and 90%, respectively. In closed-loop grasping, dense-depth feedback achieved success rates of 87.5% over all tested positions and 85% under edge-contact conditions, compared with 67.5% and 45% for raw-taxel feedback.

Problem

• tactile sensing
• human-to-robot transfer
• fingertip interaction
• contact-rich tasks
• wearable sensor

Innovation

• wearable tactile sensor
• capacitive taxel
• real-to-sim-to-real
• contact depth mapping
• human-to-robot skill transfer