Reproduce “Learning Geometry-Aware Planning Representations for Monocular Flight with Cross-Modal Supervision” 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

Wencan Feng, Bailing Tian, Yulin Hui, Zhiyu Li, Junjie Lu

GeoMonoPlan trains a monocular drone planner with depth supervision that is removed at deployment. It uses two RGB frames, metric relative pose, and vehicle state, aligning RGB planning features with a depth teacher and adding coarse-depth supervision. In simulation, average success rose from 80.0% to 91.3% versus temporal RGB-plus-feature-alignment, at similar average speeds. A separate forest flight peaked at 6.5 m/s.

Summary by alphaXiv.

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