Reproduce “Heavy Metal Acrobatics: Learning Dynamic Control for Skid-Steer Loaders” 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
Pierre-Jean Lorentz, Pascal Egli, Edo Jelavic, Cliff Li, Ramitha Sundar, Harikrishnan Suresh, Paul Montgomery, Lee Redden and 4 more
The authors train separate control skills for a five-tonne skid-steer loader in simulation using measured hydraulic behavior and a simplified rigid-body model, then transfer them to a physical John Deere 332G. The loader rocks from four wheels onto its two front wheels and balances while moving. It also traverses 75-cm undulations, though results cover tested maneuvers, not autonomous construction-site work.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.