Reproduce “Scenario-Based Motion Planning with Bounded Probability of Collision” 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

Oscar de Groot, Laura Ferranti, Dariu Gavrila, Javier Alonso-Mora

SH-MPC plans robot motion among pedestrians by constraining the probability of any collision with modeled obstacles over the full horizon. It samples joint futures and optimizes collision avoidance across them, rather than allocating risk separately by person and time step. In an eight-pedestrian Gaussian simulation, maximum observed collision probability was 1.28%, below the 5% bound; motion distributions were assumed known.

Summary by alphaXiv.

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