Safety
One-Shot Cross-Geometry Skill Transfer through Part Decomposition
arXiv:2604.15455v1 Announce Type: new Abstract: 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
arXiv:2604.15455v1 Announce Type: new Abstract: 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.
Related
- A Unified Multi-Layer Framework for Skill Acquisition from Imperfect Human Demonstrations
- Adaptor: Advancing Assistive Teleoperation with Few-Shot Learning and Cross-Operator Generalization
- WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations
- OmniUMI: Towards Physically Grounded Robot Learning via Human-Aligned Multimodal Interaction
- AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation
Source: arXiv cs.RO | 2026-04-20