Reproduce “FORCA: A Force-Aware Coding Agent for Contact-Rich Robot 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
Xiao Tan, Yixuan Wang, Zhexi Wang, Wenzhen Yuan
FORCA generates and revises robot programs for contact-rich manipulation using wrist force/torque measurements. During execution, programmed probes refine geometry and force feedback regulates motion; after each run, the agent compares force records with visual outcomes and may revise control logic. On door-handle operation, it succeeded in 10/10 trials versus 1/10 for a matched vision-only agent, without isolating individual force components.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.