Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |