Reproduce “Spin Detection in Robotic Table Tennis” 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
Jonas Tebbe, Lukas Klamt, Yapeng Gao, Andreas Zell
The authors estimate table-tennis ball spin from its curved flight, fitting smoothed three-dimensional trajectories and using the Magnus-force model. In tests, trajectory fitting classified thrower spin settings at 88.2% overall, versus 86.7% for a CNN, though it performed worse for medium and high backspin. With estimated spin, bounce-point error fell in 10 low-backspin trajectories; a KUKA robot demonstrated cooperative returns.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.