Robust Manipulation Primitive Learning via Domain Contraction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xue, Teng, Razmjoo, Amirreza, Shetty, Suhan, Calinon, Sylvain
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917803882184704
author Xue, Teng
Razmjoo, Amirreza
Shetty, Suhan
Calinon, Sylvain
author_facet Xue, Teng
Razmjoo, Amirreza
Shetty, Suhan
Calinon, Sylvain
contents Contact-rich manipulation plays an important role in human daily activities, but uncertain parameters pose significant challenges for robots to achieve comparable performance through planning and control. To address this issue, domain adaptation and domain randomization have been proposed for robust policy learning. However, they either lose the generalization ability across diverse instances or perform conservatively due to neglecting instance-specific information. In this paper, we propose a bi-level approach to learn robust manipulation primitives, including parameter-augmented policy learning using multiple models, and parameter-conditioned policy retrieval through domain contraction. This approach unifies domain randomization and domain adaptation, providing optimal behaviors while keeping generalization ability. We validate the proposed method on three contact-rich manipulation primitives: hitting, pushing, and reorientation. The experimental results showcase the superior performance of our approach in generating robust policies for instances with diverse physical parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11600
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust Manipulation Primitive Learning via Domain Contraction
Xue, Teng
Razmjoo, Amirreza
Shetty, Suhan
Calinon, Sylvain
Robotics
Contact-rich manipulation plays an important role in human daily activities, but uncertain parameters pose significant challenges for robots to achieve comparable performance through planning and control. To address this issue, domain adaptation and domain randomization have been proposed for robust policy learning. However, they either lose the generalization ability across diverse instances or perform conservatively due to neglecting instance-specific information. In this paper, we propose a bi-level approach to learn robust manipulation primitives, including parameter-augmented policy learning using multiple models, and parameter-conditioned policy retrieval through domain contraction. This approach unifies domain randomization and domain adaptation, providing optimal behaviors while keeping generalization ability. We validate the proposed method on three contact-rich manipulation primitives: hitting, pushing, and reorientation. The experimental results showcase the superior performance of our approach in generating robust policies for instances with diverse physical parameters.
title Robust Manipulation Primitive Learning via Domain Contraction
topic Robotics
url https://arxiv.org/abs/2410.11600