Reproduce “FireNav: Decision-Oriented Reconstruction Evidence Routing for Vision-Language Navigation in Indoor Fire Environments” 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

Hongbo Ding, Xiang Chen, Jiangxin Dong, Jinshan Pan

FireNav preserves the navigator’s pretrained visual pathway and selectively adds reconstruction features for decisions in smoky indoor navigation. Its router uses visual quality, task context, and execution state to choose whether and where evidence enters. On unseen simulated tests, it outperforms Restored RGB + Adapter in physical-environment success rate and SPL; real fires and physical robots remain untested.

Summary by alphaXiv.

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