Reproduce “WiTac: Wrist-Informed Tactile Representations for Contact-Rich Manipulation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Haotian He, Yiyang Chen, Congsheng Xu, Wenchao Yue, Mingze Ye, Shuai Chen, Yi Yang, Yaping Li and 4 more
WiTac fuses eight-frame tactile histories, fingertip poses, robot state, and wrist-camera features into finger-level contact representations before supplying them to a policy. On GR00T N1.7, its unweighted mean success rate across four tasks was 66.3%, versus 47.5% without wrist fusion and 37.5% for vision-only control. The evaluation covers one robot platform and four tasks.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.