Reproduce “ExoBridge: Learning a Bare Hand to Hand-Worn Exoskeleton Mapping through Human Limb Coupling” 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
Ruitong Tian, Xianyao Li, Noah B. Wilson, Fang Xu, Eric Jing Du
ExoBridge learns to predict exoskeleton contact, fingertip tactile intensity, and relative encoder motion from bare-hand video. During training, one hand is recorded bare while the other uses a sensorized exoskeleton on a separate copy of the task. Across held-out sessions in four tasks, contact AUROC is 0.916 and tactile-intensity correlation is 0.790; these are offline predictions, not closed-loop control results.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.