Learning to Push, Group, and Grasp: A Diffusion Policy Approach for Multi-Object Delivery
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_ | 1866912514036465664 |
|---|---|
| author | Yonemaru, Takahiro Wan, Weiwei Nishimura, Tatsuki Harada, Kensuke |
| author_facet | Yonemaru, Takahiro Wan, Weiwei Nishimura, Tatsuki Harada, Kensuke |
| contents | Simultaneously grasping and delivering multiple objects can significantly enhance robotic work efficiency and has been a key research focus for decades. The primary challenge lies in determining how to push objects, group them, and execute simultaneous grasping for respective groups while considering object distribution and the hardware constraints of the robot. Traditional rule-based methods struggle to flexibly adapt to diverse scenarios. To address this challenge, this paper proposes an imitation learning-based approach. We collect a series of expert demonstrations through teleoperation and train a diffusion policy network, enabling the robot to dynamically generate action sequences for pushing, grouping, and grasping, thereby facilitating efficient multi-object grasping and delivery. We conducted experiments to evaluate the method under different training dataset sizes, varying object quantities, and real-world object scenarios. The results demonstrate that the proposed approach can effectively and adaptively generate multi-object grouping and grasping strategies. With the support of more training data, imitation learning is expected to be an effective approach for solving the multi-object grasping problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_08452 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning to Push, Group, and Grasp: A Diffusion Policy Approach for Multi-Object Delivery Yonemaru, Takahiro Wan, Weiwei Nishimura, Tatsuki Harada, Kensuke Robotics Simultaneously grasping and delivering multiple objects can significantly enhance robotic work efficiency and has been a key research focus for decades. The primary challenge lies in determining how to push objects, group them, and execute simultaneous grasping for respective groups while considering object distribution and the hardware constraints of the robot. Traditional rule-based methods struggle to flexibly adapt to diverse scenarios. To address this challenge, this paper proposes an imitation learning-based approach. We collect a series of expert demonstrations through teleoperation and train a diffusion policy network, enabling the robot to dynamically generate action sequences for pushing, grouping, and grasping, thereby facilitating efficient multi-object grasping and delivery. We conducted experiments to evaluate the method under different training dataset sizes, varying object quantities, and real-world object scenarios. The results demonstrate that the proposed approach can effectively and adaptively generate multi-object grouping and grasping strategies. With the support of more training data, imitation learning is expected to be an effective approach for solving the multi-object grasping problem. |
| title | Learning to Push, Group, and Grasp: A Diffusion Policy Approach for Multi-Object Delivery |
| topic | Robotics |
| url | https://arxiv.org/abs/2502.08452 |