Reproduce “Vision-Force Admittance Learning for Peg Insertion into a Movable Hole” 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
Yuzhong Chen, Yongqing Liang, Yunzhi Xu, Irving Fang, Chase Kidder, Hui-ping Wang, Raihan Haque, Yubiao Zhang and 1 more
VFAL tackles moving-target peg insertion by combining vision with force feedback. Pose estimates guide a position-controlled robot near the hole, while poses remain soft references during contact with a learned force model. On a 3D mobile-base pushnut task, VFAL achieved 80% success and 9.22 full-wrench MSE, versus 60% and 37.82 for synchronized VFAL; this does not isolate asynchronous timing.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.