Reproduce “LocoPilot: Single-Operator Bilateral Teleoperation for Loco-Manipulation Policy Learning” 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

Antonio Langella, Giovanni Minelli, Giovanni B. Dessy, Lorenzo Amatucci, Giulio Turrisi, Victor Barasuol, Claudio Semini

LocoPilot lets an operator command a quadruped’s base and arm together, recording controller commands as training targets for a policy that uses the same interface. It estimates contact force from arm-model and motor-effort data, without a dedicated force sensor. The authors report one successful autonomous pick-and-place rollout; policy evaluation is qualitative, not a general success-rate result.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.