Reproduce “A Sparse Topometric Graph for Scalable Cross-Session Indoor Navigation” 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
Eun Sun Lee, Minkyun Seo, Gwangtak Bae, Junho Kim, Seunggu Kang, Jaesik Park, Young Min Kim
The authors introduce a sparse topometric map of traversable locations, using geometry descriptors and connectivity in a learned matcher to align partial maps and transfer goals across sessions. In Gibson navigation, it reaches a 77.14% success rate, versus 54.28% for the next-highest baseline. On 3D-FRONT, it reaches 40% under a 1 m threshold; tests cover single-floor 2D navigation, not real-world deployment.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.