Saved in:
Bibliographic Details
Main Authors: Mamedov, Shamil, Geist, A. René, Swevers, Jan, Trimpe, Sebastian
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2307.07975
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910669089013760
author Mamedov, Shamil
Geist, A. René
Swevers, Jan
Trimpe, Sebastian
author_facet Mamedov, Shamil
Geist, A. René
Swevers, Jan
Trimpe, Sebastian
contents Accurately predicting deformable linear object (DLO) dynamics is challenging, especially when the task requires a model that is both human-interpretable and computationally efficient. In this work, we draw inspiration from the pseudo-rigid body method (PRB) and model a DLO as a serial chain of rigid bodies whose internal state is unrolled through time by a dynamics network. This dynamics network is trained jointly with a physics-informed encoder that maps observed motion variables to the DLO's hidden state. To encourage the state to acquire a physically meaningful representation, we leverage the forward kinematics of the PRB model as a decoder. We demonstrate in robot experiments that the proposed DLO dynamics model provides physically interpretable predictions from partial observations while being on par with black-box models regarding prediction accuracy. The project code is available at: http://tinyurl.com/prb-networks
format Preprint
id arxiv_https___arxiv_org_abs_2307_07975
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Pseudo-rigid body networks: learning interpretable deformable object dynamics from partial observations
Mamedov, Shamil
Geist, A. René
Swevers, Jan
Trimpe, Sebastian
Robotics
Machine Learning
Accurately predicting deformable linear object (DLO) dynamics is challenging, especially when the task requires a model that is both human-interpretable and computationally efficient. In this work, we draw inspiration from the pseudo-rigid body method (PRB) and model a DLO as a serial chain of rigid bodies whose internal state is unrolled through time by a dynamics network. This dynamics network is trained jointly with a physics-informed encoder that maps observed motion variables to the DLO's hidden state. To encourage the state to acquire a physically meaningful representation, we leverage the forward kinematics of the PRB model as a decoder. We demonstrate in robot experiments that the proposed DLO dynamics model provides physically interpretable predictions from partial observations while being on par with black-box models regarding prediction accuracy. The project code is available at: http://tinyurl.com/prb-networks
title Pseudo-rigid body networks: learning interpretable deformable object dynamics from partial observations
topic Robotics
Machine Learning
url https://arxiv.org/abs/2307.07975