Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910875191869440 |
|---|---|
| author | Lv, Qi Li, Hao Deng, Xiang Shao, Rui Li, Yinchuan Hao, Jianye Gao, Longxiang Wang, Michael Yu Nie, Liqiang |
| author_facet | Lv, Qi Li, Hao Deng, Xiang Shao, Rui Li, Yinchuan Hao, Jianye Gao, Longxiang Wang, Michael Yu Nie, Liqiang |
| contents | Despite the significant success of imitation learning in robotic manipulation, its application to bimanual tasks remains highly challenging. Existing approaches mainly learn a policy to predict a distant next-best end-effector pose (NBP) and then compute the corresponding joint rotation angles for motion using inverse kinematics. However, they suffer from two important issues: (1) rarely considering the physical robotic structure, which may cause self-collisions or interferences, and (2) overlooking the kinematics constraint, which may result in the predicted poses not conforming to the actual limitations of the robot joints. In this paper, we propose Kinematics enhanced Spatial-TemporAl gRaph Diffuser (KStar Diffuser). Specifically, (1) to incorporate the physical robot structure information into action prediction, KStar Diffuser maintains a dynamic spatial-temporal graph according to the physical bimanual joint motions at continuous timesteps. This dynamic graph serves as the robot-structure condition for denoising the actions; (2) to make the NBP learning objective consistent with kinematics, we introduce the differentiable kinematics to provide the reference for optimizing KStar Diffuser. This module regularizes the policy to predict more reliable and kinematics-aware next end-effector poses. Experimental results show that our method effectively leverages the physical structural information and generates kinematics-aware actions in both simulation and real-world |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10743 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation Lv, Qi Li, Hao Deng, Xiang Shao, Rui Li, Yinchuan Hao, Jianye Gao, Longxiang Wang, Michael Yu Nie, Liqiang Robotics Machine Learning Despite the significant success of imitation learning in robotic manipulation, its application to bimanual tasks remains highly challenging. Existing approaches mainly learn a policy to predict a distant next-best end-effector pose (NBP) and then compute the corresponding joint rotation angles for motion using inverse kinematics. However, they suffer from two important issues: (1) rarely considering the physical robotic structure, which may cause self-collisions or interferences, and (2) overlooking the kinematics constraint, which may result in the predicted poses not conforming to the actual limitations of the robot joints. In this paper, we propose Kinematics enhanced Spatial-TemporAl gRaph Diffuser (KStar Diffuser). Specifically, (1) to incorporate the physical robot structure information into action prediction, KStar Diffuser maintains a dynamic spatial-temporal graph according to the physical bimanual joint motions at continuous timesteps. This dynamic graph serves as the robot-structure condition for denoising the actions; (2) to make the NBP learning objective consistent with kinematics, we introduce the differentiable kinematics to provide the reference for optimizing KStar Diffuser. This module regularizes the policy to predict more reliable and kinematics-aware next end-effector poses. Experimental results show that our method effectively leverages the physical structural information and generates kinematics-aware actions in both simulation and real-world |
| title | Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2503.10743 |