TACROSS: An Efficient and Low-Cost Scalable Human Touch System Across Heterogeneous Tactile Sensors for Dexterous Robot Learning

2026-10-08

AI Summary

This study addresses the high cost of tactile data acquisition and the signal alignment challenges arising from structural heterogeneity between human hands and robotic sensors. To overcome these limitations, this work proposes a low-cost piezoresistive five-layer tactile glove alongside a cross-modal alignment mechanism based on contact events rather than raw sensor values. A temporal Transformer is employed to map heterogeneous signals into a shared latent space, enabling a robot-centric policy learning framework for dexterous manipulation. The proposed approach increases data collection efficiency by 3.5× while reducing hardware costs by 95.7%. Furthermore, the complete software and hardware designs, along with a 150-hour tactile dataset, are released as open source to facilitate future research in tactile sensing and robotic manipulation.

Abstract

Collecting tactile demonstrations on robots is costly and slow, motivating the use of lower-cost human tactile gloves for scalable data collection. However, human capacitive/piezoresistive gloves and robotic tactile sensors differ fundamentally in transduction principle, sensor layout, spatial resolution, and dynamic response, making alignment of raw sensor channels ill-posed. To address this problem, we present TACROSS, a scalable system for learning from human touch and transferring it to robots that bridges this heterogeneity by aligning tactile streams at the level of contact events rather than raw sensor values. The hardware component of TACROSS integrates a piezoresistive glove with five layers and a cost of USD 10.86 with 285 sensing points. To align contact semantics, we design canonicalizers and residual adapters that map heterogeneous signals into a shared tactile latent with 256 dimensions via a temporal Transformer with attention across fingers. We further introduce a robot-grounded policy learning scheme in which robot demonstrations provide the sole source of ground-truth action supervision, while human demonstrations support tactile representation learning and provide confidence-weighted auxiliary supervision through valid retargeted hand targets. We evaluate our system on four contact-rich manipulation tasks. Compared to conventional teleoperation, our proposed system achieves a 3.5-fold efficiency improvement while reducing demonstration acquisition equipment cost by 95.7%. We will open-source the TACROSS hardware and software system and publicly release a tactile dataset comprising over 150 hours of recordings. Project page: https://tacross-touch-project.github.io/.

Problem

• tactile sensing
• heterogeneous sensors
• dexterous robot learning
• human-to-robot transfer
• sensor alignment

Innovation

• Cross-modal Tactile Alignment
• Temporal Transformer
• Low-cost Tactile Glove
• Dexterous Manipulation
• Policy Learning