cs.RONov 16, 2026

WiTac: Wrist-Informed Tactile Representations for Contact-Rich Manipulation

Authors: Haotian He, Yiyang Chen, Congsheng Xu, Wenchao Yue, Mingze Ye, Shuai Chen, Yi Yang, Yaping Li, 

Organizations: Sharpa Robotics · PKU · SJTU · CUHK · 

Abstract

Similar tactile contacts can call for different corrections depending on the configuration of the hand, object and target. Rather than supplying touch and wrist vision separately, fusing them before policy injection better grounds tactile features in visual context, yielding more accurate contact representations. We introduce Wrist-Informed Tactile Representations (WiTac), a pretrained encoder that learns such representations before action generation. Pretrained on nearly 300 hours of SharpaDex data, WiTac deeply fuses tactile signals with hand motion and wrist views into a comprehensive contact representation. Conditioning downstream VLA policies (GR00T N1.7 and π0.5π_{0.5}) on WiTac substantially improves task success over vision-only base policies across four contact-rich manipulation tasks (+28.8% and +15.0% on average), and further outperforms a wrist-free tactile encoder by 18.8% and 7.5%, respectively. Offline analyses further show that incorporating wrist vision yields more accurate contact descriptors, stronger joint task-contact discrimination, greater feature stability under tactile noise, and clearer action-direction readout from similar contacts. Project page: https://wrist-informed-tactile-representations.github.io/.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. VT-WAM: Visual-Tactile World Action Model for Contact-Rich Manipulation

    Jul 2, 2026Shuai Tian, Yupeng Zheng, Yuhang Zheng +7Contact-Rich Robotic ManipulationWorld Action Models

  2. TACTIC: Understanding Tactile Encoders and Conditioning for Contact-rich Robot Manipulation Policies

    Sep 25, 2026Seongjin Bien, Débora Oliveira Makowski, Carlo Kneissl +6Visuo-Tactile Representation LearningVision-Based Tactile Sensing