Pick-and-place Manipulation Across Grippers Without Retraining: A Learning-optimization Diffusion Policy Approach
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917932527779840 |
|---|---|
| author | Yao, Xiangtong Zhou, Yirui Meng, Yuan Dong, Liangyu Hong, Lin Zhang, Zitao Bing, Zhenshan Huang, Kai Sun, Fuchun Knoll, Alois |
| author_facet | Yao, Xiangtong Zhou, Yirui Meng, Yuan Dong, Liangyu Hong, Lin Zhang, Zitao Bing, Zhenshan Huang, Kai Sun, Fuchun Knoll, Alois |
| contents | Current robotic pick-and-place policies typically require consistent gripper configurations across training and inference. This constraint imposes high retraining or fine-tuning costs, especially for imitation learning-based approaches, when adapting to new end-effectors. To mitigate this issue, we present a diffusion-based policy with a hybrid learning-optimization framework, enabling zero-shot adaptation to novel grippers without additional data collection for retraining policy. During training, the policy learns manipulation primitives from demonstrations collected using a base gripper. At inference, a diffusion-based optimization strategy dynamically enforces kinematic and safety constraints, ensuring that generated trajectories align with the physical properties of unseen grippers. This is achieved through a constrained denoising procedure that adapts trajectories to gripper-specific parameters (e.g., tool-center-point offsets, jaw widths) while preserving collision avoidance and task feasibility. We validate our method on a Franka Panda robot across six gripper configurations, including 3D-printed fingertips, flexible silicone gripper, and Robotiq 2F-85 gripper. Our approach achieves a 93.3% average task success rate across grippers (vs. 23.3-26.7% for diffusion policy baselines), supporting tool-center-point variations of 16-23.5 cm and jaw widths of 7.5-11.5 cm. The results demonstrate that constrained diffusion enables robust cross-gripper manipulation while maintaining the sample efficiency of imitation learning, eliminating the need for gripper-specific retraining. Video and code are available at https://github.com/yaoxt3/GADP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15613 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pick-and-place Manipulation Across Grippers Without Retraining: A Learning-optimization Diffusion Policy Approach Yao, Xiangtong Zhou, Yirui Meng, Yuan Dong, Liangyu Hong, Lin Zhang, Zitao Bing, Zhenshan Huang, Kai Sun, Fuchun Knoll, Alois Robotics Current robotic pick-and-place policies typically require consistent gripper configurations across training and inference. This constraint imposes high retraining or fine-tuning costs, especially for imitation learning-based approaches, when adapting to new end-effectors. To mitigate this issue, we present a diffusion-based policy with a hybrid learning-optimization framework, enabling zero-shot adaptation to novel grippers without additional data collection for retraining policy. During training, the policy learns manipulation primitives from demonstrations collected using a base gripper. At inference, a diffusion-based optimization strategy dynamically enforces kinematic and safety constraints, ensuring that generated trajectories align with the physical properties of unseen grippers. This is achieved through a constrained denoising procedure that adapts trajectories to gripper-specific parameters (e.g., tool-center-point offsets, jaw widths) while preserving collision avoidance and task feasibility. We validate our method on a Franka Panda robot across six gripper configurations, including 3D-printed fingertips, flexible silicone gripper, and Robotiq 2F-85 gripper. Our approach achieves a 93.3% average task success rate across grippers (vs. 23.3-26.7% for diffusion policy baselines), supporting tool-center-point variations of 16-23.5 cm and jaw widths of 7.5-11.5 cm. The results demonstrate that constrained diffusion enables robust cross-gripper manipulation while maintaining the sample efficiency of imitation learning, eliminating the need for gripper-specific retraining. Video and code are available at https://github.com/yaoxt3/GADP. |
| title | Pick-and-place Manipulation Across Grippers Without Retraining: A Learning-optimization Diffusion Policy Approach |
| topic | Robotics |
| url | https://arxiv.org/abs/2502.15613 |