Learning to Transfer In-Hand Manipulations Using a Greedy Shape Curriculum
Loading...
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
In-hand object manipulation is challenging to simulate due to complex contact dynamics, non-repetitive finger gaits, and the need to indirectly control unactuated objects. Further adapting a successful manipulation skill to new objects with different shapes and physical properties is a similarly challenging problem. In this work, we show that natural and robust in-hand manipulation of simple objects in a dynamic simulation can be learned from a high quality motion capture example via deep reinforcement learning with careful designs of the imitation learning problem. We apply our approach on both single-handed and two-handed dexterous manipulations of diverse object shapes and motions. We then demonstrate further adaptation of the example motion to a more complex shape through curriculum learning on intermediate shapes morphed between the source and target object. While a naive curriculum of progressive morphs often falls short, we propose a simple greedy curriculum search algorithm that can successfully apply to a range of objects such as a teapot, bunny, bottle, train, and elephant.
Description
CCS Concepts: Computing methodologies -> Physical simulation; Motion capture; Reinforcement learning; Learning from demonstrations
@article{10.1111:cgf.14741,
journal = {Computer Graphics Forum},
title = {{Learning to Transfer In-Hand Manipulations Using a Greedy Shape Curriculum}},
author = {Zhang, Yunbo and Clegg, Alexander and Ha, Sehoon and Turk, Greg and Ye, Yuting},
year = {2023},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.14741}
}