Reproduce “Learning Scene-Aware Humanoid Locomotion through 3D Clutter from Immersive Human Demonstrations” 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
Beichen Wang, Tong Xu, Daniel Kosukhin, Yuen-Hei Yeung, Yuanjie Lu, Xuesu Xiao
MTC captures human demonstrations in robot-scaled virtual clutter, retargeting them into motions that account for obstacle clearance before training a traversal policy. An 80-frame look-ahead improves retargeting over per-frame solving. The generalist reaches 70.2% corridor success versus 42.2% for CAT; this is a benchmark result, not a physical corridor trial.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.