Reproduce “Deep Radar Inverse Sensor Models for Dynamic Occupancy Grid Maps” 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
Zihang Wei, Rujiao Yan, Matthias Schreier
The authors learn a single-scan radar-to-grid model that predicts free, occupied, and unknown cells in a local polar grid from LiDAR-derived labels, then combines it with Doppler measurements for dynamic grid mapping. In Cartesian comparisons, conditional free and occupied estimates improve from 60.26% to 85.74% and 15.30% to 38.68%, respectively; evidence comes from highway tests with one radar type.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.