TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916644827168768 |
|---|---|
| author | Wu, Yansong Chen, Zongxie Wu, Fan Chen, Lingyun Zhang, Liding Bing, Zhenshan Swikir, Abdalla Haddadin, Sami Knoll, Alois |
| author_facet | Wu, Yansong Chen, Zongxie Wu, Fan Chen, Lingyun Zhang, Liding Bing, Zhenshan Swikir, Abdalla Haddadin, Sami Knoll, Alois |
| contents | Assembly is a crucial skill for robots in both modern manufacturing and service robotics. However, mastering transferable insertion skills that can handle a variety of high-precision assembly tasks remains a significant challenge. This paper presents a novel framework that utilizes diffusion models to generate 6D wrench for high-precision tactile robotic insertion tasks. It learns from demonstrations performed on a single task and achieves a zero-shot transfer success rate of 95.7% across various novel high-precision tasks. Our method effectively inherits the self-adaptability demonstrated by our previous work. In this framework, we address the frequency misalignment between the diffusion policy and the real-time control loop with a dynamic system-based filter, significantly improving the task success rate by 9.15%. Furthermore, we provide a practical guideline regarding the trade-off between diffusion models' inference ability and speed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_11047 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulation Wu, Yansong Chen, Zongxie Wu, Fan Chen, Lingyun Zhang, Liding Bing, Zhenshan Swikir, Abdalla Haddadin, Sami Knoll, Alois Robotics Assembly is a crucial skill for robots in both modern manufacturing and service robotics. However, mastering transferable insertion skills that can handle a variety of high-precision assembly tasks remains a significant challenge. This paper presents a novel framework that utilizes diffusion models to generate 6D wrench for high-precision tactile robotic insertion tasks. It learns from demonstrations performed on a single task and achieves a zero-shot transfer success rate of 95.7% across various novel high-precision tasks. Our method effectively inherits the self-adaptability demonstrated by our previous work. In this framework, we address the frequency misalignment between the diffusion policy and the real-time control loop with a dynamic system-based filter, significantly improving the task success rate by 9.15%. Furthermore, we provide a practical guideline regarding the trade-off between diffusion models' inference ability and speed. |
| title | TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2409.11047 |