Robotics: Science and Systems XIX
DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training
Aleksei Petrenko, Arthur Allshire, Gavriel State, Ankur Handa, Viktor MakoviychukAbstract:
In this work, we propose algorithms and methods that enable learning dexterous object manipulation using simulated one- or two-armed robots equipped with multi-fingered hand end-effectors. Using a parallel GPU-accelerated physics simulator (Isaac Gym), we implement challenging tasks for these robots, including regrasping, grasp-and-throw, and object reorientation. To solve these problems we introduce a decentralized Population-Based Training (PBT) algorithm that allows us to massively amplify the exploration capabilities of deep reinforcement learning. We find that this method significantly outperforms regular end-to-end learning and is able to discover robust control policies in challenging tasks. Video demonstrations of learned behaviors and the code can be found at https://sites.google.com/view/dexpbt
Bibtex:
@INPROCEEDINGS{Petrenko-RSS-23, AUTHOR = {Aleksei Petrenko AND Arthur Allshire AND Gavriel State AND Ankur Handa AND Viktor Makoviychuk}, TITLE = {{DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training}}, BOOKTITLE = {Proceedings of Robotics: Science and Systems}, YEAR = {2023}, ADDRESS = {Daegu, Republic of Korea}, MONTH = {July}, DOI = {10.15607/RSS.2023.XIX.037} }