Reproduce “PhantomTac: Hijacking Robotic Tactile Systems with Deploy-and-forget Tags” 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
Binbin Zhang, Yifeng Zhang, Xiaomeng Chen, Dongyao Chen
PhantomTac maps target sensor responses to small magnets, then uses a battery-free tag to inject chosen false force readings. In tests, positive normal-force injection made a Dofbot stop grasping early and drop a box, while negative injection damaged it. Offset success exceeded 95% through 8 mm in that setup; shear attacks were not demonstrated on a robot.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.