Reproduce “A Structured Prediction Approach for Robot Imitation 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

Anqing Duan, Iason Batzianoulis, Raffaello Camoriano, Lorenzo Rosasco, Daniele Pucci, Aude Billard

The authors propose a structured-prediction framework for imitation learning that models probabilistic trajectories while respecting Euclidean or manifold-valued outputs. Kernel-based weights and selectable divergence losses support different imitation modes and trajectory modulation. In a KUKA spherical-polishing task, the robot reproduced and adapted its motion to requested points, though occasional small tool–ball deviations remained.

Summary by alphaXiv.

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