Reproduce “ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich 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
Peiyuan Tang, Yao Li, Xiaodong Zhang, Wuyang Zhang, Qin Xia, Yanyong Zhang, Zijiang Yang
ForceLDM trains a student policy for contact-rich robot manipulation by distilling representations from a teacher with privileged future force and optical-flow inputs. At deployment, the student uses current multimodal observations, including force history, without the teacher or future signals. Across five tasks, it averages 87.1% in-distribution success, versus 72.2% for Seer with Force; it does not lead on every task.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.