GRIP: A General Robotic Incremental Potential Contact Simulation Dataset for Unified Deformable-Rigid Coupled Grasping
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915369931767808 |
|---|---|
| author | Ma, Siyu Du, Wenxin Yu, Chang Jiang, Ying Zong, Zeshun Xie, Tianyi Chen, Yunuo Yang, Yin Han, Xuchen Jiang, Chenfanfu |
| author_facet | Ma, Siyu Du, Wenxin Yu, Chang Jiang, Ying Zong, Zeshun Xie, Tianyi Chen, Yunuo Yang, Yin Han, Xuchen Jiang, Chenfanfu |
| contents | Grasping is fundamental to robotic manipulation, and recent advances in large-scale grasping datasets have provided essential training data and evaluation benchmarks, accelerating the development of learning-based methods for robust object grasping. However, most existing datasets exclude deformable bodies due to the lack of scalable, robust simulation pipelines, limiting the development of generalizable models for compliant grippers and soft manipulands. To address these challenges, we present GRIP, a General Robotic Incremental Potential contact simulation dataset for universal grasping. GRIP leverages an optimized Incremental Potential Contact (IPC)-based simulator for multi-environment data generation, achieving up to 48x speedup while ensuring efficient, intersection- and inversion-free simulations for compliant grippers and deformable objects. Our fully automated pipeline generates and evaluates diverse grasp interactions across 1,200 objects and 100,000 grasp poses, incorporating both soft and rigid grippers. The GRIP dataset enables applications such as neural grasp generation and stress field prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05020 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GRIP: A General Robotic Incremental Potential Contact Simulation Dataset for Unified Deformable-Rigid Coupled Grasping Ma, Siyu Du, Wenxin Yu, Chang Jiang, Ying Zong, Zeshun Xie, Tianyi Chen, Yunuo Yang, Yin Han, Xuchen Jiang, Chenfanfu Robotics Graphics Grasping is fundamental to robotic manipulation, and recent advances in large-scale grasping datasets have provided essential training data and evaluation benchmarks, accelerating the development of learning-based methods for robust object grasping. However, most existing datasets exclude deformable bodies due to the lack of scalable, robust simulation pipelines, limiting the development of generalizable models for compliant grippers and soft manipulands. To address these challenges, we present GRIP, a General Robotic Incremental Potential contact simulation dataset for universal grasping. GRIP leverages an optimized Incremental Potential Contact (IPC)-based simulator for multi-environment data generation, achieving up to 48x speedup while ensuring efficient, intersection- and inversion-free simulations for compliant grippers and deformable objects. Our fully automated pipeline generates and evaluates diverse grasp interactions across 1,200 objects and 100,000 grasp poses, incorporating both soft and rigid grippers. The GRIP dataset enables applications such as neural grasp generation and stress field prediction. |
| title | GRIP: A General Robotic Incremental Potential Contact Simulation Dataset for Unified Deformable-Rigid Coupled Grasping |
| topic | Robotics Graphics |
| url | https://arxiv.org/abs/2503.05020 |