Reproduce “PRoMiSe: Persistent Multi-Robot Monitoring Sim-to-Real-to-Field” 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
Alessio Salvatore, Juan de los Rios, David Rytz, Maria Stamatopoulou
PRoMiSe trains a shared policy in lightweight 2D simulation to control patrol robots using local sensing, idleness summaries, teammate information, and recurrent memory. The policy issues body-frame velocity commands and transfers to new sites without fine-tuning or a patrol graph. In a matched 300-second industrial-site test, two robots achieved 318-second average idleness and 50% coverage, not full coverage.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.