Reproduce “Polygraph: Large-Scale Multi-Session Trajectory Optimization using Pose Graphs” 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

Petar Lukovic, Tian Yi Lim, Marc Pollefeys, Pablo Speciale, Hermann Blum, Zuria Bauer

Polygraph links repeated robot traversals by matching keyframe clusters and admitting cross-session connections only after independent candidate placements agree. It optimizes a shared pose graph without reconstructing a 3D scene. Across six evaluation conditions, the gate admitted 1,025 edges with 0.646 m translation error, versus 1.639 m without the gate; these are pre-optimization edge errors, not final trajectory accuracy.

Summary by alphaXiv.

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