Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.15455 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913040547446784 |
|---|---|
| author | Thompson, Skye Biza, Ondrej Konidaris, George |
| author_facet | Thompson, Skye Biza, Ondrej Konidaris, George |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15455 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | One-Shot Cross-Geometry Skill Transfer through Part Decomposition Thompson, Skye Biza, Ondrej Konidaris, George Robotics 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. |
| title | One-Shot Cross-Geometry Skill Transfer through Part Decomposition |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.15455 |