Robotics: Science and Systems XXII

TactAlign: Human-to-Robot Policy Transfer via Tactile Alignment

Youngsun Wi, Jessica Yin, Elvis Xiang, Akash Sharma, Jitendra Malik, Mustafa Mukadam, Nima Fazeli, Tess Hellebrekers

Abstract:

Human demonstrations collected by wearable devices (e.g., tactile gloves) provide fast and dexterous supervision for policy learning, and are guided by rich, natural tactile feedback. However, a key challenge is how to transfer human-collected tactile signals to robots despite the differences in sensing modalities and embodiment. Existing human-to-robot (H2R) approaches that incorporate touch often assume identical tactile sensors, require paired data, and involve little to no embodiment gap between human demonstrator and the robots, limiting scalability and generality. We propose TactAlign, a cross-embodiment tactile alignment method that transfers human-collected tactile signals to a robot with different embodiment. TactAlign transforms human and robot tactile observations into an shared latent representation using a rectified flow, without paired datasets, manual labels, or privileged information. Our method enables low-cost latent transport guided by hand-object interaction-derived pseudo-pairs. We demonstrate that TactAlign improves H2R policy transfer across multiple contact-rich tasks (pivoting, insertion, lid closing), generalizes to unseen objects and tasks with human data (approximately 5 minutes), and enables zero-shot H2R transfer on a highly dexterous tasks (light bulb screwing).

Download:

Bibtex:

  
@INPROCEEDINGS{WiY-RSS-26, 
    AUTHOR    = {Youngsun Wi AND Jessica Yin AND Elvis Xiang AND Akash Sharma AND Jitendra Malik AND Mustafa Mukadam AND Nima Fazeli AND Tess Hellebrekers}, 
    TITLE     = {{TactAlign: Human-to-Robot Policy Transfer via Tactile Alignment}}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2026}, 
    ADDRESS   = {Sydney, Australia}, 
    MONTH     = {July}, 
    DOI       = {10.15607/RSS.2026.XXII.006} 
}