Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Learning dexterous in-hand manipulation:

Learning dexterous in-hand manipulation: We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies that can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed in a simulated environment in which we randomize many of the physical properties of the system such as friction coefficients and an object’s appearance. Our policies transfer to the physical robot despite being trained entirely in simulation. Our method does not rely on any human demonstrations, but many behaviors found in human manipulation emerge naturally, including finger gaiting, multi-finger coordination, and the controlled use of gravity. Our results were obtained using the same distributed RL system that was used to train OpenAI Five. We also include a video of our results: https://youtu.be/jwSbzNHGflM. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png The International Journal of Robotics Research SAGE

Loading next page...
 
/lp/sage/learning-dexterous-in-hand-manipulation-i70Z4uNa2L

References (76)

Publisher
SAGE
Copyright
Copyright © 2022 by SAGE Publications
ISSN
0278-3649
eISSN
1741-3176
DOI
10.1177/0278364919887447
Publisher site
See Article on Publisher Site

Abstract

We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies that can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed in a simulated environment in which we randomize many of the physical properties of the system such as friction coefficients and an object’s appearance. Our policies transfer to the physical robot despite being trained entirely in simulation. Our method does not rely on any human demonstrations, but many behaviors found in human manipulation emerge naturally, including finger gaiting, multi-finger coordination, and the controlled use of gravity. Our results were obtained using the same distributed RL system that was used to train OpenAI Five. We also include a video of our results: https://youtu.be/jwSbzNHGflM.

Journal

The International Journal of Robotics ResearchSAGE

Published: Nov 18, 2019

Keywords: Dexterous manipulation; multifingered hands; adaptive control; learning and adaptive systems; humanoid robots

There are no references for this article.