Reproduce “HLO-AMP: Hierarchical Loco-Manipulation from Object-Aware Motion Priors” 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
Jean-Pierre Sleiman, Bilal Hammoud, He Li, Jonathan Foster, Sylvain Bertrand, Jessica K. Hodgins, Farbod Farshidian
HLO-AMP trains a low-level controller with retargeted motions and the box present, then freezes it while a high-level policy learns box transport using commands clipped to the controller’s training-data envelope. In simulation, it succeeds in 80.7%, versus 77.1% for a force-surrogate controller, with fewer dropped boxes. Hardware trials succeed at 7 kg in 2 of 3 attempts but fail at 8 kg.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.