Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2407.21172 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910548070760448 |
|---|---|
| author | Puang, En Yen Li, Zechen Chew, Chee Meng Luo, Shan Wu, Yan |
| author_facet | Puang, En Yen Li, Zechen Chew, Chee Meng Luo, Shan Wu, Yan |
| contents | Measuring grasp stability is an important skill for dexterous robot manipulation tasks, which can be inferred from haptic information with a tactile sensor. Control policies have to detect rotational displacement and slippage from tactile feedback, and determine a re-grasp strategy in term of location and force. Classic stable grasp task only trains control policies to solve for re-grasp location with objects of fixed center of gravity. In this work, we propose a revamped version of stable grasp task that optimises both re-grasp location and gripping force for objects with unknown and moving center of gravity. We tackle this task with a model-free, end-to-end Transformer-based reinforcement learning framework. We show that our approach is able to solve both objectives after training in both simulation and in a real-world setup with zero-shot transfer. We also provide performance analysis of different models to understand the dynamics of optimizing two opposing objectives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_21172 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Stable Robot Grasping with Transformer-based Tactile Control Policies Puang, En Yen Li, Zechen Chew, Chee Meng Luo, Shan Wu, Yan Robotics Measuring grasp stability is an important skill for dexterous robot manipulation tasks, which can be inferred from haptic information with a tactile sensor. Control policies have to detect rotational displacement and slippage from tactile feedback, and determine a re-grasp strategy in term of location and force. Classic stable grasp task only trains control policies to solve for re-grasp location with objects of fixed center of gravity. In this work, we propose a revamped version of stable grasp task that optimises both re-grasp location and gripping force for objects with unknown and moving center of gravity. We tackle this task with a model-free, end-to-end Transformer-based reinforcement learning framework. We show that our approach is able to solve both objectives after training in both simulation and in a real-world setup with zero-shot transfer. We also provide performance analysis of different models to understand the dynamics of optimizing two opposing objectives. |
| title | Learning Stable Robot Grasping with Transformer-based Tactile Control Policies |
| topic | Robotics |
| url | https://arxiv.org/abs/2407.21172 |