Given a demonstration, a robot should be able to generalize a skill to any object it encounters-but existing approaches to skill transfer often fail to adapt to objects with unfamiliar shapes. Motivated by examples of improved transfer from compositional modeling, we propose a method for improving transfer by decomposing objects into their constituent semantic parts. We leverage data-efficient generative shape models to accurately transfer interaction points from the parts of a demonstration object to a novel object. We autonomously construct an objective to optimize the alignment of those points on skill-relevant object parts. Our method generalizes to a wider range of object geometries than existing work, and achieves successful one-shot transfer for a range of skills and objects from a single demonstration, in both simulated and real environments.
@article{arxiv.2604.15455,
title = {One-Shot Cross-Geometry Skill Transfer through Part Decomposition},
author = {Skye Thompson and Ondrej Biza and George Konidaris},
journal= {arXiv preprint arXiv:2604.15455},
year = {2026}
}