One-Shot Cross-Geometry Skill Transfer through Part Decomposition
Enables robots to generalize manipulation skills to objects with diverse shapes from a single demonstration, addressing a key limitation in skill transfer for robotics.
Proposed a method using part decomposition and generative shape models to transfer robot skills from a single demonstration to novel objects with unfamiliar geometries, achieving successful one-shot transfer across a range of skills and objects in simulation and real environments.
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.