Reproduce “Beyond Terminal Constraints: Reliable Robot Control with Learned Safe Sets” 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

Gianni Lunardi, Elias Fontanari, Matteo Saveriano, Andrea Del Prete

RC-MPC moves a learned safe-set constraint across the prediction horizon, making the set a return point rather than only a terminal constraint. The paper gives conditional recursive-feasibility results for three MPC schemes. In 400 simulations, RC-MPC failed fewer than 2% of tasks at horizon N=45 and margin α≥30%; this does not certify the learned set meets required assumptions.

Summary by alphaXiv.

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