Reproduce “CoCoNav: Conformal Control for Safe Robot Navigation in Crowds” 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
Cheng Guo, Mingzhe Ni, Zheng Liang, Yihu Ling, Yuan Hu, Michele Caprio, Daniele Pucci, Wei Pan
CoCoNav separates route generation from safety verification for robot navigation among pedestrians. It uses online, horizon-specific proportional–integral updates to calibrate conformal bounds from delayed forecast errors, then checks proposed actions against those bounds. CPI-MPC raises minimum distance from 0.52±0.08 m to 0.56±0.04 m versus Soft-Only MPC, with longer travel time; this ablation reports no success or collision rates.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.