Reproduce “Mobility-Budget-Constrained Submodular Maximization for Distributed Semantic Multi-Robot Exploration” 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
Changxuan Yao, Sandilya Sai Garimella, Lu Gan, Panagiotis Tsiotras
Semantic-RAG plans robot routes by balancing expected semantic information gain against terrain and turn costs and mobility budgets, then coordinates choices among neighboring robots. It uses a Dirichlet map and filters over-budget routes. In ten gridworld runs, it achieved 94.1% coverage and 82.5% mIoU, versus 79.9% and 68.3% for shortest-distance selection. In simulation, its mapping means were not statistically separated.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.