Reproduce “MR-COGraphs: Communication-efficient Multi-Robot Open-vocabulary Mapping System via 3D Scene 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
Qiuyi Gu, Zhaocheng Ye, Jincheng Yu, Jiahao Tang, Tinghao Yi, Yuhan Dong, Jian Wang, Jinqiang Cui and 2 more
The authors present a compact object-and-relationship map for sharing open-vocabulary information between robots. Each object’s 512-dimensional semantic feature is encoded as 3 dimensions for transmission and reconstructed by the receiving robot; matching objects help align maps. In a real-world test, transmitted data fell from 10.3 KB to 0.44 KB with the same 0.213 m translation error, using Record3D localization labeled “GT.”
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.