Shape-based transfer of generic skills
Published in IEEE International Conference on Robotics and Automation (ICRA),, 2021
We propose a new, data-efficient approach for skill transfer to novel objects, accounting for known categorical shape variation. A low-dimensional shape representation embedding is learned from a set of deformations, sampled between known objects within a category. This latent representation is mapped to a set of control parameters that result in successful execution of a category-level skill on that object. This method generalizes a learned manipulation policy to unseen objects with few training examples. We demonstrate this approach on pouring from cups and scooping with spatulas, where there is complex, nonlinear variation of successful control parameters across objects.
Recommended citation: S. Thompson, L. P. Kaelbling and T. Lozano-Perez, "Shape-Based Transfer of Generic Skills," ICRA, 2021
Download Paper | Download Bibtex