Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.07688 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915125007482880 |
|---|---|
| author | Obrist, Jan Zamora, Miguel Zheng, Hehui Hinchet, Ronan Ozdemir, Firat Zarate, Juan Katzschmann, Robert K. Coros, Stelian |
| author_facet | Obrist, Jan Zamora, Miguel Zheng, Hehui Hinchet, Ronan Ozdemir, Firat Zarate, Juan Katzschmann, Robert K. Coros, Stelian |
| contents | Data-driven methods have shown great potential in solving challenging manipulation tasks; however, their application in the domain of deformable objects has been constrained, in part, by the lack of data. To address this lack, we propose PokeFlex, a dataset featuring real-world multimodal data that is paired and annotated. The modalities include 3D textured meshes, point clouds, RGB images, and depth maps. Such data can be leveraged for several downstream tasks, such as online 3D mesh reconstruction, and it can potentially enable underexplored applications such as the real-world deployment of traditional control methods based on mesh simulations. To deal with the challenges posed by real-world 3D mesh reconstruction, we leverage a professional volumetric capture system that allows complete 360° reconstruction. PokeFlex consists of 18 deformable objects with varying stiffness and shapes. Deformations are generated by dropping objects onto a flat surface or by poking the objects with a robot arm. Interaction wrenches and contact locations are also reported for the latter case. Using different data modalities, we demonstrated a use case for our dataset training models that, given the novelty of the multimodal nature of Pokeflex, constitute the state-of-the-art in multi-object online template-based mesh reconstruction from multimodal data, to the best of our knowledge. We refer the reader to our website ( https://pokeflex-dataset.github.io/ ) for further demos and examples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07688 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PokeFlex: A Real-World Dataset of Volumetric Deformable Objects for Robotics Obrist, Jan Zamora, Miguel Zheng, Hehui Hinchet, Ronan Ozdemir, Firat Zarate, Juan Katzschmann, Robert K. Coros, Stelian Robotics Computer Vision and Pattern Recognition Data-driven methods have shown great potential in solving challenging manipulation tasks; however, their application in the domain of deformable objects has been constrained, in part, by the lack of data. To address this lack, we propose PokeFlex, a dataset featuring real-world multimodal data that is paired and annotated. The modalities include 3D textured meshes, point clouds, RGB images, and depth maps. Such data can be leveraged for several downstream tasks, such as online 3D mesh reconstruction, and it can potentially enable underexplored applications such as the real-world deployment of traditional control methods based on mesh simulations. To deal with the challenges posed by real-world 3D mesh reconstruction, we leverage a professional volumetric capture system that allows complete 360° reconstruction. PokeFlex consists of 18 deformable objects with varying stiffness and shapes. Deformations are generated by dropping objects onto a flat surface or by poking the objects with a robot arm. Interaction wrenches and contact locations are also reported for the latter case. Using different data modalities, we demonstrated a use case for our dataset training models that, given the novelty of the multimodal nature of Pokeflex, constitute the state-of-the-art in multi-object online template-based mesh reconstruction from multimodal data, to the best of our knowledge. We refer the reader to our website ( https://pokeflex-dataset.github.io/ ) for further demos and examples. |
| title | PokeFlex: A Real-World Dataset of Volumetric Deformable Objects for Robotics |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.07688 |