Reproduce “Open-World Object Motion Anticipation via Meta-Learned Semantic Adaptation” 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
Mason Peterson, Gage MacLin, Camilla Tabasso, Jonathan P. How, Joshua Migdal, Tye Brady, Taskin Padir
The authors introduce a model predicting whether static objects will move within three seconds. It combines visual features, spatial relationships, and scene history, adapting to unseen objects without test-time weight updates. In 20 simulated scenes, it avoided collisions in all cases, averaging 68.5 seconds to completion, 3.7 seconds slower than the all-static planner. This test used ground-truth state inputs, not hardware.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.