Reproduce “Learning the Dynamics of Deformable Linear Objects Through Coupled Oscillators for Bimanual Robotic 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

Iván López-Broceño, Maximilian Stölzle, Daniel Feliu-Talegon, Daniela Rus, Cosimo Della Santina

Φ-CON learns cable dynamics from marker motion and endpoint forces using a translation-invariant model. It estimates elastic and gravitational forces for target shapes, adding them as feedforward to PD feedback. In tests, it reduced endpoint error on a real cable by a reported mean 27.9% versus PD impedance control; this result is limited to tested targets and does not establish physical global stability.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.