Reproduce “AVALON: Zero-Shot Indoor Navigation with Human-Seeded Topological Memory” 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

Jing Xia, Changyan Li, Yuduo Wang, Guiyin Tian, Bo Wang, Yifan Liao, Mingjun Li, Shiyan Hu

AVALON enables first-mission service robot navigation using user floor plans and place clues. It builds a topological graph, follows graph-guided point goals, and verifies semantic landmarks with visual evidence and odometry checks. On one 12.81-meter office route, it completed five of five trials with 46.4-second deployment time, versus 78.5 seconds for DimOS-Go2.

Summary by alphaXiv.

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